Every equity research team has a process for analysis.

Almost none of them have a process for memory.

The model gets built. The thesis gets written. The calls get made. But the decisions, why a company got dropped, why the timeline shifted, what the CIO flagged in the last review, those live in someone’s head. Or in a email body nobody can find. Or nowhere at all.

Six weeks into a research project, half the context is gone.

Not because analysts are careless. Because there was never a system to capture it in the first place.

This is the problem Claude Cowork solves, but only if you set it up correctly. Out of the box, Claude has no memory of your project either. Every new session starts blank. You re-explain the coverage universe. You re-brief the thesis. You rebuild what you already built.

The fix is a context system. A set of structured files that Claude reads at the start of every session, updates as decisions get made, and references automatically when something changes.

Four phases. One source of truth. Zero re-explaining.

Here is the full workflow.

The Problem With How Most Teams Use AI

Most finance teams using AI today are getting outputs, not leverage.

Ask a question. Get an answer. Close the tab. Start over tomorrow.

The problem is not the tool. The problem is that every session starts from zero. Claude does not know your coverage universe. It does not know why you dropped that company last week. It does not know what the CIO flagged in the last review. It does not know your thesis shifted.

So you explain it again.

And again next session.

And again the session after that.

You are not building anything. You are running in place with a faster pair of shoes.

The teams getting real leverage are not using Claude to answer questions. They are using it to run projects. Where context compounds. Where a decision made in week two automatically updates the timeline, the risk register, and the stakeholder communications. Where nothing gets lost because everything gets written down in files Claude can actually read.

That is what this workflow builds.

The Four-Phase Workflow

Phase 1 and Phase 2: Building the Foundation

First, the setup.

If you are starting with Claude Projects, create a new Project in Claude and name it after your research report. Upload your initial research notes, any earnings transcripts you already have, and the three skill files from the download bundle at the end of this newsletter.

If you are on Claude Cowork, open the desktop app, click the folder icon, and point it at the project folder on your computer. Claude can now read, create, and edit every file in that folder directly.

Either way, you are ready to start Phase 1.

Phase 1: Project Intelligence

This is the most important phase in the entire workflow. Before you plan anything, you teach Claude everything about the project.

Everything that follows- the plan, the risk register, the stakeholder communications is built from one file:

project-definition.md

If this file is thorough, every session after it gets easier. If you rush it, you rebuild context forever. Run this prompt to start the discovery session:

You are an expert project manager conducting comprehensive discovery for an equity research project. Ask me one question at a time. After each response, summarise what you have learned before moving on.

Cover these areas in order:
1. Research objectives — what question must the final report answer?
2. Coverage universe — which companies are covered and why?
3. Stakeholders — who needs this, what does each person need from it, and how do they prefer to receive updates?
4. Deadline structure — milestones from data gathering through to publication.
5. Known risks and data gaps.
6. Historical context from any previous coverage of this sector.

When we are done, save everything as project-definition.md.

Claude will ask you one question at a time. Answer each one specifically. The more detail you give here, the sharper every output that follows will be.

The session takes 30 to 45 minutes if you know your project well.

When it is done, run the premortem prompt immediately, before you move to planning:

Conduct a premortem on this research project. Imagine it is six months from now and the report failed — missed deadlines, wrong thesis, stakeholder alignment broke down. Based on everything you know about this project, what are the most likely failure modes? Rank them by likelihood and impact. Add these to project-definition.md.

Phase 2: Structured Architecture

Now you convert the project-definition.md file into a live project plan.

Four artifacts. Four prompts. Run them in sequence.

A. The Work Breakdown Structure

Using project-definition.md, generate a work breakdown structure for this research project. Decompose it into phases (data gathering, analysis, drafting, review, publication), tasks, and subtasks. For each task include: estimated duration, dependencies, responsible party, and priority level. Save as wbs.md.

This gives you every task in the project, who owns it, how long it takes, and what it depends on. For a four-company sector report, expect 25 to 35 tasks across five phases.

B. The Risk Register

Convert the premortem risks from project-definition.md into a risk register. For each risk include: description, likelihood (High/Medium/Low), impact (High/Medium/Low), mitigation strategy, owner, and trigger indicators that tell you when to act. Save as risk-register.md.

The trigger indicators are the most important column. They tell you exactly what to watch for, so risks don’t surprise you, they get flagged before they land.

C. The Stakeholder Communications Plan

Using the stakeholder information from project-definition.md, create a stakeholder communication plan. For each stakeholder define: their information needs, update frequency, preferred format, and trigger events that warrant immediate communication. Save as stakeholder-comms-plan.md.

Every stakeholder gets a different update.

The CIO gets 150 words on milestones and risks. The junior analyst gets a numbered task list. The portfolio manager gets recommendations and risk/reward. One prompt. Three individualised communication plans.

D. The Gantt Chart

Generate a Gantt chart for this research project as a CSV file. Use this column format: Outline Level, ID, Name, Start, Finish, Duration, % Complete, Predecessors, Resource Names. Save as gantt-export.csv.

Once the CSV is saved, upload it to OnlineGantt.com, free, no account required. You get a full colour-coded visual timeline with dependencies in under two minutes.

At the end of Phase 2 your project folder looks like this:

research-project/
├── project-definition.md
├── wbs.md
├── risk-register.md
├── stakeholder-comms-plan.md
├── gantt-export.csv
└── skills/
    ├── finance-decision-log-skill.md
    ├── finance-risk-review-skill.md
    └── finance-stakeholder-update-skill.md

One folder. Every file Claude needs to run this project. Always current. Always readable.

The plan is built. Now the project has to survive contact with reality.

Phase 3: When the Project Fights Back

This is where most research projects break down.

Not in the planning. Not in the modelling. In the middle. When something changes and the carefully built plan suddenly has a hole in it.

A company reports earnings during the drafting window. A thesis assumption gets challenged by new data. A coverage decision gets reversed. And suddenly you are manually updating five different documents, re-briefing three different people, and trying to remember what you decided three weeks ago and why.

This is where the context system earns its keep.

Phase 3 is execution. And execution means change. The workflow handles it through three tools- a decision log, a status snapshot, and a risk review, all triggered by single prompts that update the project files automatically.

The Decision Log

Every significant decision gets captured immediately after it is made.

Not batched at end of week. Not summarised from memory. Immediately. Details disappear within 24 hours. A log written on Friday about a decision made on Tuesday is a guess, not a record.

The decision log skill handles this. (download this skill from the download bundle at the end of this newsletter.) If you are on Claude Projects, add the contents of finance-decision-log-skill.md as a Project file. If you are on Claude Cowork, upload the file in a skills subsection inside your customize section, Claude loads it automatically.

Then trigger it like this:

Trigger the finance-decision-log skill.

We are dropping [Company X] from the coverage universe. Reason: the most recent earnings call revealed the original thesis no longer holds.

Log this decision, assess the impact on wbs.md and risk-register.md, and draft a brief stakeholder update explaining the change.

Claude reads the project files, identifies every task that referenced that company, assesses the impact on the timeline and risk register, and writes the log entry in a format anyone can read six months from now and understand in under 30 seconds.

Here is what the entry looks like when NVIDIA reports earnings mid-project and your model assumptions need updating:

---
Date: 2026-04-24
Decision ID: DEC-001
Status: Active

Decision:
NVIDIA earnings released mid-project. Model assumptions updated to reflect 
Q1 FY2027 actuals before first draft.

Context:
NVIDIA reported Q1 FY2027 results on April 23, 2026. Data center revenue 
came in 12% above consensus. Sovereign AI procurement cited as primary 
upside driver. Bear case assumption on post-2027 demand deceleration 
materially challenged.

Alternatives considered:
- Proceed with existing model, flag earnings as post-publication update: 
  rejected — actuals are material to the valuation.
- Delay publication by one week: rejected — CIO sign-off window does not 
  permit extension without client communication.

Rationale:
Model refresh checkpoint was built into the plan for this scenario. 
48-hour fast-update protocol activated. Publication date May 18 maintained.

Impact:
- Task 3.5 (model refresh) activated immediately
- NVIDIA sovereign AI upside case promoted from option to base case
- Risk R-02 moves from Stable to Triggered and Resolved

Decided by: Senior Analyst, Research Head
---

Every decision. Every rationale. Every impact. Permanent record.

The Risk Review

Place finance-risk-review-skill.md in the skills folder/section. Trigger it after any significant project change or market event:

Trigger the finance-risk-review skill. 

NVIDIA reported earnings yesterday — data center revenue 12% above 
consensus, sovereign AI cited as primary driver. Scan the risk register 
against current project state and flag anything that needs action today.

Claude reads the risk register, cross-references it against the current WBS and any recent decisions, and classifies every risk as Escalating, Stable, Reduced, or New.

Escalating risks get a specific recommended next step. Not a general suggestion. One action, clearly stated.

The Status Snapshot

Once a week or after any major change — run this:

Write a project status snapshot as of today. Include: overall health 
(Green / Yellow / Red), progress against milestones, active risks, 
decisions made this week, and the top priorities for the next seven days. 
Save as status-snapshot-YYYY-MM-DD.md.

The snapshot becomes your weekly briefing, your CIO update source, and your project memory, all in one file.

Three tools. One principle.

Nothing gets lost. Information compounds. Everything stays connected to the project, the decisions, and the files.

Phase 4: The Automation Stack

This is where Claude Cowork separates itself from every other AI workflow.

Phases 1, 2, and 3 are prompts you run. Phase 4 is tasks that run without you.

Claude Cowork has a scheduling feature. You set a task once, define when it runs, and it executes automatically, reading your project files, generating the output, and saving it for your review. No prompting. No remembering. No manual trigger.

Three scheduled tasks. Add them in this order. Do not add the next one until the previous one is working.

Task 1: The Weekly Briefing

This is the one to start with.

Every Monday at 8am, Claude reads your WBS, your risk register, and any recent status snapshots. It drafts a full weekly report, progress against milestones, active risks, decisions made last week, and top priorities for the coming week. Saved as a file for your review before anyone else sees it.

Set it up with this command in Claude Cowork:

/schedule weekly monday 8am

Review wbs.md, risk-register.md, and any recent status-snapshot files. 
Draft a weekly status report covering: progress against milestones, active 
risks, decisions made this week, and the top priorities for the coming week. 
Save as weekly-update-YYYY-MM-DD.md and notify me for review.

Time saved: 45 to 60 minutes every week.

Task 2: The Daily Risk Check

Add this after week one, once you have seen the weekly briefing work at least once.

Every weekday at 9am, Claude scans your risk register for anything rated High likelihood or High impact. It cross-references against current project status. If any trigger indicators are showing, it flags them and suggests immediate actions.

/schedule weekdays 9am

Scan risk-register.md for any risks rated High likelihood or High impact. 
Check against current project status in wbs.md. If any trigger indicators 
are showing, flag them and suggest immediate actions. Save as 
risk-check-YYYY-MM-DD.md.

Time saved: 10 to 15 minutes every day.

Task 3: Friday Stakeholder Drafts

Add this after two weeks, once the daily risk check is running cleanly.

Every Friday at 3pm, Claude triggers the stakeholder update skill, reviews all project changes from the week, and drafts individualised updates for every stakeholder, formatted exactly according to the communications plan you built in Phase 2.

/schedule weekly friday 3pm

Trigger the finance-stakeholder-update skill. Review all project changes 
from this week. Draft individualised updates for each stakeholder per 
stakeholder-comms-plan.md. Present all drafts for review before sending.

The Research Head gets 150 words on milestones and risks. The portfolio managers get recommendations and positioning updates. The junior analyst gets a task list for next week. Three different updates. Zero manual drafting.

Time saved: 30 to 40 minutes every week.

Two things to know before you set these up.

Your Mac needs to be awake and Claude Cowork needs to be open for scheduled tasks to run. If the computer is asleep at the scheduled time, the task runs when it wakes. And do not automate anything that goes directly to an external stakeholder until you have reviewed the outputs manually for at least two weeks.

Let the automation handle internal tracking first. Extend it outward once you trust what it produces.

That is the full stack. Four phases. One project folder. A research workflow that remembers everything, updates itself when things change, and runs its own Monday briefing while you sleep.

Get the Full System

The full guide is free.

I put together a detailed resource that walks through this entire workflow, every phase, every prompt, every file, and the complete skill bundle. The project-definition.md discovery prompt, the WBS generator, the risk register, all three skill files, and the Gantt CSV template. Ready to drop into your own project folder and run.

No newsletter summary. The whole thing.

Download Full Research Bundle

If you want to go deeper, there is a premium membership on shikshannivesh.com. You get access to premium workflows, masterclasses, and free consultancy sessions. Everything we build, you get first.

🤝 Help Us Grow This Circle

Share Alpha with AI

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

We believe investing should start with understanding and every newsletter we write is built to reflect that.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

It’s 9:45 on a Monday morning.

You have 30 client portfolios to review. Markets opened 45 minutes ago. Your phone is already going. And you haven’t even looked at what moved over the weekend.

But here’s the thing, you already knew this was coming. Every Sunday night. Every single one. That slow dread of Monday morning prep that never gets shorter, never gets easier, and always feels like you’re running before you’ve even started.

Most wealth advisors I talk to spend 2 to 3 hours on this. Pulling data. Cross-referencing watchlists. Checking who’s overdue for a review. Manually building a call priority list in their head, or worse, in a spreadsheet.

Therefore, they walk into client calls half-prepared. Reactive, not proactive.

I used to be the same. Until I built one workflow on Claude Cowork that replaced all of it.

The industry is still doing this the old way. And AI content is making it worse.

Here’s the truth nobody in wealth management wants to say out loud.

The prep work hasn’t changed in 20 years. Advisors are still doing manually what their seniors did manually. Pull the data. Check the notes. Build the priority list. Rinse, repeat, burn out.

But the AI content you see online? It’s all ChatGPT screenshots and 10-step frameworks that look impressive and do nothing. Nobody is actually building the workflow, running it with real clients, and showing you what it looks like at 9:45 on a Monday.

Therefore, most advisors either stay stuck in the old way or they try some AI tool once, it doesn’t work out of the box, and they go back to the spreadsheet.

I’m not interested in talking about AI. I’m interested in showing you the exact session I ran, the two plugins I used, and the output I had in 20 minutes.

Here's exactly what I did: step by step

I opened Claude Cowork on a Monday morning with two plugins active: the Wealth Management plugin and the S&P Global plugin.

Plugin direct links: Both plugins are available inside Claude Cowork's plugin directory. You can also install them directly from the links below.

• Wealth Management plugin: https://claude.com/plugins/wealth-management

• S&P Global plugin: https://claude.com/plugins/sp-global

Select your working folder.

Open a folder on your desktop. This is where everything lives. Your source files, your firm’s report template, any compliance language you want included. Click the folder icon in Claude Cowork and point it to that folder. Whatever you put in there, Claude can read and use. That is the whole setup.

Here’s how it ran:

Step 1: Priority call list in minutes. I asked Claude to pull my top clients by portfolio size and flag anyone overdue for a review. It cross-referenced my watchlist and surfaced 5 names immediately, the ones that actually needed a call that week, not a generic list of 30.

Step 2: Market context for each client. For each of those 5, I asked for a quick brief, what moved in their holdings over the weekend, any earnings or macro events relevant to their positions. The S&P Global plugin pulled live data directly into the session.

Step 3: Call talking points, pre-built. Before I picked up the phone, I had a short brief for each client. What to lead with. What risk to flag. What opportunity to mention.

That’s it. Three steps. One session. Done before my first coffee went cold.

But here’s what surprised me the most, it wasn’t just faster. The calls were better. I walked in with context, not chaos.

What the output actually looks like

I’m not going to describe it. I’m going to show you.

That list took under 4 minutes to generate. Five names. Each one flagged with a reason, overdue review, portfolio drift, earnings impact on a holding.

But here’s what most people miss when they see this.

They think the value is the speed. It’s not.

The real value is that you stop making decisions on instinct at 9:45 in the morning when you’re already behind. You walk into every call with a structured brief. You sound like you’ve been tracking that client all week, because now, effectively, you have.

Therefore, the client experience changes. Not slightly. Noticeably.

One session. Two plugins. And your Monday morning goes from controlled chaos to something that actually feels like a system.

The exact prompts to run this yourself

Open Claude Cowork. Make sure both plugins are active i.e., Wealth Management and S&P Global. Then run these three prompts in sequence.

Prompt 1: Build your priority call list:

“Review my client portfolio list and flag the top 5 clients who need a call this week. Prioritize by portfolio size, overdue reviews, and any significant market movement in their holdings.”

Prompt 2: Get market context per client:

“For each of the 5 clients flagged, pull a brief on what moved in their holdings over the past week and any upcoming earnings or macro events relevant to their positions.”

Prompt 3 — Generate call talking points:

“For each client, give me 2 to 3 talking points I should lead with on the call, one risk to flag, one opportunity to mention, and one action item.”

That’s the full session. Three prompts. One output. Ready before your first call.

That’s the full workflow, but if you want to go deeper

Everything you need to run this on Monday is in this newsletter.

The three prompts above will get you the output. The two plugins are free to install. The session takes 20 minutes.

But if you want more, a detailed walkthrough, additional prompt variations that produce the same output through a different path, and a structured reference you can keep coming back to, I’ve put together a full resource guide on the website.

It covers the same workflow in more depth. Think of this newsletter as the quick start. The guide is the manual.

You’ll find it at https://shikshannivesh.com/research-in-action/goodbye-monday-morning-panic-the-claude-cowork-wealth-management-workflow

This is just the beginning

I built this for a client who was drowning in Monday morning prep.

Three prompts. Two plugins. Twenty minutes. That was the brief, and that’s what we delivered.

It’s not complex. But it works. And that’s the only bar that matters.

If you’re a wealth advisor spending hours on prep that could be automated, try this. It costs you nothing.

P.S. I’m exploring something very exciting with Claude next and if it works the way I think it will, it’s going to be the most useful thing I’ve shared this year. Stay tuned.

🤝 Help Us Grow This Circle

Share Alpha with AI

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

We believe investing should start with understanding and every newsletter we write is built to reflect that.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

One of the most under-discussed problems in investing is not valuation.

It’s time allocation.

Most investors don’t lose money because they lack information. They lose money because they spend weeks researching businesses that were never worth that effort in the first place.

Over time, I realised something uncomfortable.

Deep research is not the starting point.

Filtering is.

This article explains the 60-minute AI-assisted workflow I now use to decide whether a company deserves deeper research at all. Not whether it’s a “good” or “bad” company. Just whether it has earned more of my time.

The Real Objective: Time, Not Certainty

This process is not designed to produce conviction.

It’s designed to answer a much simpler question:

Is this business clear, durable, and understandable enough to justify deeper work right now?

That distinction matters.

A company can be excellent and still fail this filter.

That doesn’t make it a bad business.

It just means the signal is too weak, too noisy, or too complex at this stage.

Time is capital. This workflow is about allocating it rationally.

Why AI Fits This Stage Perfectly

AI is often misused in investing.

People try to outsource judgment to it.

That’s backwards.

Where AI actually shines is compression:

• compressing documents,

• compressing years of disclosures,

• compressing complexity into first-order signals.

In this workflow, AI does not decide anything.

It simply speeds up the part that humans are worst at doing efficiently.

Judgment stays human.

Step 1: AI Deep Business Review

The first step is an AI-driven deep business review.

The goal here is not summarisation.

It’s to understand the economic engine of the business.

At this stage, I want clarity on:

• what the company actually sells,

• where revenue and profits truly come from,

• how margins differ across segments,

• how capital-intensive the business is,

• whether returns are driven by structure or circumstance,

• and what the real risks look like beneath the surface.

I treat this like an acquisition-style review, not a stock pitch.

This step alone eliminates a surprising number of companies.

If the economics are weak, fragile, or overly dependent on narratives, I stop.

No models. No valuation. No sunk-cost fallacy.

→ First, use Gemini with DeepSearch to generate an expert-level business analysis.

Prompt for deep research:

You are a senior equity research analyst and portfolio manager with experience evaluating businesses for long-term capital allocation.

Your task is to analyze [COMPANY NAME] as if you were deciding whether to deploy meaningful capital into the business, or acquire it outright.

The objective is not to summarize the company.
The objective is to understand how the business actually makes money, how durable that engine is, and whether it deserves deeper research time.

TIME PERIOD (MANDATORY):
Use data strictly from FY2021 to FY2025.
If FY2025 is not fully available, use the latest available FY results and explicitly state the cutoff.

Base your analysis ONLY on high-signal sources:
- Official company filings and annual reports (FY2021–FY2025)
- Investor presentations (FY2021–FY2025)
- Earnings call transcripts (FY2021–FY2025)
- Peer disclosures for comparison
- Credible industry and market research
- Expert commentary where relevant

Avoid promotional language.
Avoid repeating management narratives.
Write as if this analysis will be reviewed in an internal investment committee.

Structure your analysis as follows:

1. Business Reality Check (FY2021–FY2025)
- What does the company actually sell, and to whom?
- Revenue breakdown by product, geography, and channel (FY2021–FY2025)
- Where is real economic value created?
- Branded vs non-branded mix (if applicable)
- Customer concentration and buying behavior
- Seasonality and cyclicality
- Segment-level margin structure
- Has the business generated sufficient internal cash to fund growth during FY2021–FY2025?

2. Market Position and Competitive Edge
- Realistic addressable market the company can capture today
- Structural tailwinds and headwinds visible in FY2021–FY2025
- Direct and indirect competitors
- Sources of competitive advantage (pricing, brand, scale, distribution, cost)
- Evidence of pricing power in the last 5 years
- Durability of advantages over the next 5–10 years
- External risks that could structurally impair the business

3. Financial Engine Quality (FY2021–FY2025)
- Revenue, EBIT, and free cash flow trends (FY2021–FY2025)
- Margin stability and volatility across the period
- ROIC relative to cost of capital
- Capital reinvestment efficiency
- Capex and working capital intensity
- Balance sheet strength and dilution history
- Predictability and quality of free cash flows

4. Growth Reality Test
- What actually drove growth from FY2021 to FY2025?
- What management claims will drive growth next?
- Which growth levers are realistically executable?
- Rank growth levers by impact on profitability and returns
- What would need to go right to materially grow earnings over the next 3–5 years?

5. Management and Capital Allocation Discipline
- Key decision-makers and leadership structure
- Ownership and incentive alignment
- Execution track record over FY2021–FY2025
- Capital allocation behavior (capex, M&A, dividends, buybacks)
- Consistency of strategy over time

6. Risk, Fragility, and Hidden Optionality
- Top structural risks evident today
- Downside scenarios and failure modes
- Risk mitigants
- Underappreciated assets or strategic levers

Final output must include:
- A concise executive summary written for an investment committee
- A clearly labeled FY2021–FY2025 financial snapshot
- Segment- and geography-level economics
- Moat durability assessment
- Ranked growth levers
- Capital allocation scorecard
- Risk map with commentary

Do not speculate.
If data for any FY year is unavailable, explicitly state so.
All judgments must be grounded in evidence.

A free Gemini account is sufficient.

Step 2: One-Page Business Compression

If the business survives the first step, I compress everything into a single-page visual summary.

→ I compress the entire analysis into a one-page infographic.
This forces clarity on revenue pools, profit drivers, capex needs, working capital pressure, and where value is really created.

This is a forcing function.

A one-page view makes it very hard to hide:

• poor ROIC,

• messy segment economics,

• bloated capex,

• or unclear value drivers.

It also reveals something important very quickly.

Whether the business has a coherent shape.

In my experience, genuinely strong businesses tend to become clearer when compressed.

Weak or overly complex businesses become more confusing.

If I cannot understand the company on one page, I pause.

Not because the company is bad.

But because it hasn’t earned deeper time yet.

Step 3: Understanding Check

The final step is the most misunderstood.

→ Third, I test my understanding using a quiz generated from the same analysis.
Not factual questions. Business mechanics.

By asking questions like:

• Why do margins differ across segments?

• Which segment actually drives returns?

• What breaks first in a downturn?

This is not an intelligence test.

It’s a clarity test.

If, even after the deep review and one-page compression, the answers still don’t click, one of two things is true:

• the business model is genuinely complex and requires much deeper work, or

• the signal-to-noise ratio is too low for a quick filter.

In both cases, I don’t proceed further at this stage.

That’s not rejection.

That’s discipline.

What This Workflow Is (and Is Not)

This process is:

• a time-allocation filter,

• a bias-reduction tool,

• a way to avoid falling in love with “interesting” companies.

It is not:

• a replacement for full research,

• a valuation framework,

• or a shortcut to conviction.

It simply ensures that when I do go deep, I’m doing so on businesses that have already demonstrated clarity, durability, and economic logic.

The Edge Is the Combination

AI compresses weeks of analyst work into under an hour.

Human judgment decides whether the idea survives.

Used this way, AI doesn’t make investing easier.

It makes it cleaner.

And in markets, cleanliness of thinking is often more valuable than speed.

The full guide is free. And there is more where this came from.

I put together a detailed resource guide that walks through this entire workflow, every step, and the prompts used. Free to download on the website.

If you want to go deeper, there is a premium membership on shikshannivesh.com. You get access to premium workflows, masterclasses, and free consultancy sessions. Everything we build, you get first.

[Download the guide here: https://shikshannivesh.com/research-in-action/the-60-minute-filter-using-gemini ]

P.S. This was the 60-minute filter. Next issue, I am running the same AI-first approach on a live portfolio using the Wealth Management Plugin. Same idea. Different domain. If you want to see what that looks like, make sure you are subscribed.

🤝 Help Us Grow This Circle

Share Alpha with AI

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

We believe investing should start with understanding and every newsletter we write is built to reflect that.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

People who do equity research are not lazy. They are some of the most detail-oriented professionals in finance. They read annual reports for fun. They build models on weekends. They argue about EV/EBITDA multiples at dinner. The work is not the problem. But the process has a ceiling. If one research report takes you three days, you cover two companies a month. That is the ceiling. Not your skill. Not your effort. Time. And if you could do the same quality work in 90 minutes, you would not stop doing research. You would do ten times more of it.

This is not about doing less. It is about doing more.

Most conversations about AI in finance frame it as a replacement. Faster, cheaper, fewer analysts. That is the wrong frame entirely. The best researchers are not going to stop doing research because a tool speeds them up. They are going to do more of it. Better coverage. More companies. Sharper theses. Efficiency does not kill the craft. It expands it. The analyst who covers ten companies with the same effort that used to cover two is not doing less work. They are doing the work that actually matters, ten times over.

This is the Claude Cowork workflow that built the report. Let me walk you through it.

Step 1: Download Claude app and install the Equity Research Plugin.

Go to claude.ai and download the Claude desktop app. Switch to Claude Cowork section. Once it is open, search for the Equity Research Plugin in the plugin library, or go directly to claude.com/plugins/equity-research. Install it. That is it. The whole setup takes under ten minutes and you do not need to touch a single line of code.

Step 2: Select your working folder.

Open a folder on your desktop. This is where everything lives. Your source files, your firm’s report template, any compliance language you want included. Click the folder icon in Claude Cowork and point it to that folder. Whatever you put in there, Claude can read and use. That is the whole setup.

Step 3: Type your instruction in plain English.

No prompt engineering. No special syntax. Just tell Claude what you want the same way you would brief a colleague. For this report, the instruction was simple: initiate coverage on Hitachi Energy India, build the financial model, run the valuation, write the investment thesis. That was it. One paragraph. Claude Cowork handled the rest.

Note: Claude asked for access to my Chrome browser mid-run. It gave me two steps, download the Claude for Chrome extension and sign in. Once I did, it connected automatically and continued. No manual setup beyond that.

Step 4: Let it run. Do not interrupt.

This is the part that feels different the first time. Claude starts pulling data from primary sources: company investor relations pages, BSE and NSE filing portals, Screener.in. It builds the financial model. It writes the investment thesis. It structures the report. You are not doing any of this. You are watching it happen. The instinct is to jump in and correct things mid-run. Resist that. Let it finish. You will have the full output in front of you to audit, challenge, and refine. But first, let it complete the job you gave it.

Step 5: Drop in your template and watch it reformat.

Once the report is generated, take your firm’s template, your Word document, your branded layout, your fonts and colours and drop it into the working folder. Tell Claude Cowork to reformat the output using that template. It reads the structure, matches the layout, and produces the report in your format. Not approximately. Exactly. The output looks like something your firm produced, because in every way that matters, it did.

In this walkthrough, I instructed to add the firm template after the report was already generated. I did that deliberately, to show you the difference between the raw output and the branded output side by side. But this is not how you do it once you start running this regularly.

Before you type your first instruction, put everything into the working folder. Your report template. Your logo. Your brand guidelines. Your colour palette. Your fonts. Your Excel financial model format, if you have one. All of it goes in once, at the start. Claude reads what is in that folder and works within those parameters from the beginning. Every report it generates from that point will come out in your format automatically. You do not reformat after the fact. You do not add a step at the end. The branded output is just the output.

This is a one-time setup. Once it is done, it is done.

Step 6: Audit the output. This is where your expertise matters most.

The report is in front of you. Now read it like a critic, not a cheerleader. Check the assumptions in the financial model against your own view of the business. Push back on the investment thesis. Ask whether the risks section captures what you actually know about the sector. If something is wrong, correct it. If something is missing, add it. The debugging and audit will take another hour, sometimes two. But here is the point: generation plus audit is still a fraction of what the traditional process takes. You are not saving 90 minutes. You are saving two to three days. And you are spending that recovered time doing the one thing that actually requires you, which is thinking.

When it comes to debugging the model, you have three options. The one I prefer is Claude in Excel, you open the Claude plugin directly inside your spreadsheet, describe what is wrong, and it fixes it in the workbook itself. You can ask it to debug formulas, explain what a sheet is doing, or rebuild a section entirely. You can also ask Claude to debug it in the Claude Cowork chat if you prefer staying in one place. Or you can do it manually, the way you always have. All three work.

This is not about replacing the analyst. It is about what the analyst does next.

The research does not get worse when the execution gets faster. It gets better. You have more time to challenge the thesis. More time to stress test the model. More time to cover companies you never had bandwidth for. The workflow handles the mechanical work. You handle everything that matters. That is the shift. And once you have seen it, you cannot unsee it.

The full guide is free. And there is more where this came from.

I put together a detailed resource guide that walks through this entire workflow, every step, every screenshot, and the prompts used. It is on the website, free to download.

If you want to go deeper, there is a premium membership on shikshannivesh.com. You get access to premium workflows, masterclasses, and free consultancy sessions. Everything we build, you get first.

[Download it here: https://shikshannivesh.com/research-in-action/ai-equity-research-with-claude-cowork]

P.S. This was the equity research workflow. Next issue, I am running Claude Cowork on a live portfolio using the Wealth Management Plugin. Same idea. Different domain. If you want to see what that looks like, make sure you are subscribed.

🤝 Help Us Grow This Circle

Share Alpha with AI

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

We believe investing should start with understanding and every newsletter we write is built to reflect that.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Let me be honest with you.

Every month, I dread compliance week.

Not because I don’t understand the numbers, but because turning a bank statement into proper accounting entries, tracking down payment gateway fees, identifying GST implications, and making sure everything ties to the last rupee… that process has always been manual. And manual means slow, and slow means I push it to the last possible day.

This February, I decided to try something different. I handed all of it to Claude Cowork.

Here’s what happened, step by step, no theory, just the actual workflow.

What I Started With

Three files:

• A bank statement CSV from My Bank: 22 transactions, 01–28 February 2026

• A Cashfree transactions CSV: 200 rows of payment gateway settlement data

• A Cashfree tax invoice PDF: the GST invoice for processing fees (HSN codes, IGST, everything)

No Excel template. No journal entry format. No prior setup. Just three raw files dropped into the workspace folder.

The Workflow: What I Typed, What Claude Did

Step 1: Journal Entries from the Bank Statement

My first prompt was simple:

Prompt → Debit Entries and Credit Entries Connecting to Sales invoices Purchase invoices in Bank Statement in Excel with an Explanation. I need this for the month of February from 1st of February to 28th of February 2026.

What came back: a 5-sheet Excel workbook.

• Bank Statement tab: all 22 transactions with a running balance column

• Journal Entries tab: full double-entry lines for every transaction, with narrations

• Sales Invoices tab: categorised receipts

• Purchase Invoices tab: categorised payments (bank charges, software subscriptions, taxes, transfers)

• Summary tab: opening balance, total receipts, total payments, closing balance

Every debit had a matching credit. Every line was labelled. The closing balance matched the bank statement to the rupee.

Step 2: “Can You Recheck Everything?”

I got a little confused looking at the summary sheet.

In double-entry accounting, the journal totals always appear equal on both sides, that’s how the system is designed. I didn’t know that. So I asked Claude to explain it, recheck every number, and rebuild the summary so it was clear to a non-accountant.

It did exactly that. Broke it down into plain language. Rebuilt the sheet.

The closing balance matched the bank statement exactly.

Zero discrepancy.

Step 3: Adding the Payment Gateway Data

I uploaded two more files, a transaction CSV from my payment gateway and their monthly GST invoice PDF.

Claude read both, matched them to the bank entries, identified the applicable, HSN codes for the processing fees, separated the exempt and taxable portions, flagged the IGST input credit, and built a compound journal entry for it.

It also flagged a small rounding difference between the invoice net and the actual bank credit, labelled it, documented it, didn’t hide it.

Two new sheets were automatically added to both workbooks.

I typed one prompt. It handled the accounting logic, the GST categorisation, and the cross-file reconciliation.

The Feature That Surprised Me Most: LinkedIn Redaction

Once everything was done, I wanted to share some of this publicly, but the workbook had real account numbers, IFSC codes, and gateway IDs in it.

One prompt: *”Create a duplicate for LinkedIn. Mask all identifiers. Keep all the accounting intact.”*

Claude scanned every cell across all seven sheets and replaced every sensitive identifier — account numbers, IFSC codes, gateway entity IDs, customer contact details, with masked placeholders. The financial data, the dates, the narrations, the formulas, all preserved exactly as they were.

It even caught a false positive mid-scan and self-corrected without me pointing it out.

This is now my standard process for anything I share publicly.

One compliance file. One shareable file. Both produced in the same session.

What Claude Cowork Actually Is

This is worth pausing on, because a lot of people ask me:

*”Are you uploading your financial data to some server somewhere?”*

No.

Claude Cowork is a desktop application. When you run it, you give it access to exactly one folder on your computer. That folder and only that folder is what it can read and write to. Nothing else.

Your files don’t leave your machine. They’re not sent to a third-party server.

They’re not stored in a cloud database. Claude processes the content in memory during the session, produces the output files, and that’s it.

For financial professionals, this matters. You’re not pasting client data into a chat interface. You’re not uploading sensitive documents to an unknown server.

You select a folder. You work. The files stay where they are.

That’s a meaningful difference.

This Was One Workflow. The Tool Does Much More.

What I built here was an accounting and compliance workflow.

But Claude Cowork has purpose-built skills for a much wider range of professional work.

Explore plugins here

A few I’ve been exploring:

- **Equity Research**: morning notes, earnings analyses, initiating coverage reports,

sector overviews, full financial models. The kind of output that used to take

an analyst a full day.

- **Investment Banking**: CIMs, teasers, pitch decks, buyer lists, merger models.

Drop in the source data, get a structured first draft.

- **Private Equity**: IC memos, due diligence checklists, LBO models,

value creation plans. Built for deal teams.

- **Financial Analysis**: DCF models, comps analyses, 3-statement models,

variance analysis. With proper Excel formatting, not just a table in a chat.

- **Sales & Marketing**: outreach sequences, competitive intelligence,

campaign plans, performance reports.

Each of these is a “skill”, a pre-built workflow that Claude knows how to run.

You bring the context. It handles the structure, the formatting, and the output.

The compliance workflow I showed you is honestly one of the simpler ones.

The more complex skills, a proper equity research initiation report, a full LBO model, a CIM for a sell-side process, those are what make this genuinely different from just “asking ChatGPT to help with Excel.”

**If You Want to See How This Works for Your Business**

I run a short call for people who want to understand whether and how this fits their workflow. No pitch. Just a practical walkthrough based on your specific context.

https://shikshannivesh.com/services

Or reply to this email directly, I read all of them.

If this was useful, share it with one person in finance or research who’s still doing this kind of work manually.

See you next week.

— Shubham

🤝 Help Us Grow This Circle

Share Alpha with AI

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

We believe investing should start with understanding and every newsletter we write is built to reflect that.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Why Sell-Side Research is Expensive Fiction

Sell-side analysts might be the most insulated people in the stock market today.

On the last week of January, a former client forwarded me a report: hold your $1.5 Mn Infosys position for 35% upside. Why? Because the firm was adopting AI to “boost efficiency”.

I genuinely laughed.

The people paid thousands of dollars to analyze tech stocks are often the last to see structural shifts. While they were tweaking their DCF models, the friction to build software had collapsed to nearly zero. I’m not a traditional software engineer, yet I had just shipped two functional applications in a single month using Claude and Cursor.

I told my client the analyst’s thesis was broken. The very next week, the market agreed. Following the Friday launch of Anthropic’s new enterprise AI agents, Indian IT stocks dumped 7% on February 4th along with global tech selloff. The traditional IT services moat wasn’t expanding, it was evaporating.

here is my post on linkedin from morning of 👉 31st of Jan.

The $300 Billion Wake-Up Call

The carnage wasn’t limited to offshore IT. A sudden jolt rippled through the technology sector in early February 2026, when nearly $300 billion in market value vanished in about a single trading day, forcing investors to rethink where value truly sits in the age of artificial intelligence. High-margin data and legal service providers experienced even steeper drops. Stocks like Thomson Reuters and LegalZoom slid 15% to 20% as markets priced in the risk that AI agents could handle legal research, drafting, and triage.

But while Wall Street was panicking over the death of the “billable hour,” they completely missed the flip side of the equation. If AI agents can execute complex legal and coding workflows for a fraction of the cost, the friction to build a business drops to near zero. We are witnessing a massive supply shock. Because anyone can now “vibe-code” an app into existence, the market is being flooded with new software.

How a $319 App Changes the Global Economy

A client sent me a post from X this week that perfectly captures why the old IT model is collapsing.

A non-technical founder just launched a “Bhagavad-Gita daily” iOS app. He built the entire thing himself using a $200 Claude Code subscription, $20 for ChatGPT Pro, and a $99 Apple developer fee.

He shipped a complete, functional app for $319.

When the cost of building software drops this close to zero, supply explodes. We are looking at a vibe coding market projected to hit $325 billion by 2040. Hundreds of thousands of new applications are about to flood the market.

This creates a massive third-order impact. The hardest part of launching a startup is no longer writing the code. The new bottleneck is getting people to actually care. Every single app that gets vibe-coded into existence now has to fight for distribution. They all have to navigate the exact same post-ship lifecycle to survive.

The "Growth Tax" on the Infinite App Boom

Shipping an app for $319 is a miracle. But building an app and building a business are two entirely different games.

The moment that Bhagavad-Gita app goes live on the App Store, the “build” phase ends, and the “grow” phase begins. And the grow phase is an expensive gauntlet. To turn that app into a revenue-generating asset, the founder has to pay what I call the “Growth Tax.”

Every single vibe-coded app has to pay these four taxes to survive:

1. The Attention Tax (Acquisition): How do users find the app? The founder has to buy them. That means running a $50 ad test on Instagram or Google Search. (The Winners: Meta, Alphabet)

2. The Plumbing Tax (Operations): If the app goes viral, the servers will melt. Founders need edge caching, cloud hosting, and DDoS protection just to keep the lights on. (The Winners: Cloudflare, AWS, Datadog)

3. The Trust Tax (Security): Users won’t pay for a buggy, unsecured app. It requires enterprise-grade identity verification and bot protection. (The Winners: Okta, Auth0)

4. The Habit Tax (Retention): A daily quote app only works if people open it daily. Founders have to pay for push notifications and email flows to retain users. (The Winners: Twilio, HubSpot)

The legacy analysts missed this because they don’t build software. They don’t see the tollbooths that capture a fraction of a cent every time one of these new apps scales.

The "SuperAnalyst" Tollbooth Screener

I don’t want you to just take my word for this. I want you to spot these capital rotations before the sell-side analysts figure it out.

The old model of waiting for a 40-page PDF report is dead. The market moves too fast. To spot these “tollbooth” beneficiaries before they show up in an earnings report, you need to run the numbers yourself.

Open up ChatGPT, Claude, Perplexity, or My personal favourite (Gemini) & select deep research and run this exact research prompt. This isn't a basic question; it is an institutional-grade research protocol designed to force the AI to map both the public winners and the private market threats.

# SYSTEM CONTEXT & ANALYTICAL MANDATE
You are a Lead Institutional Technology Equities Analyst. Your mandate is to execute a rigorous, data-backed screening protocol to identify the exact public equities that will capture exponential revenue from the "Infinite App Supply Shock." 
Context: Vibe-coding and AI agents (e.g., Claude, Cursor) have collapsed the cost of building software to near zero. As hundreds of thousands of new applications flood the market, the absolute bottleneck for startups has officially shifted from *building* the product to *growing*, *hosting*, and *securing* it.

# SCOPE & CONSTRAINTS
- Target Asset Class: PUBLIC EQUITIES ONLY (US and Global) for the final watchlist.
- Private Company Treatment: You MUST deeply analyze the impact of massive private companies (e.g., Stripe, Vercel, OpenAI) that are capturing the "Growth Tax" spend or threatening public players. You must strictly label them as [PRIVATE] and never recommend them as investable targets.

# MODULE 1: THE "GROWTH TAX" OPPORTUNITY MAP
Map the exact path of capital a founder must spend after an app goes live. Define the operational triggers for these four non-negotiable "Taxes" every app pays to survive:
1. The Attention Tax (Ad-tech, performance marketing, app store optimization)
2. The Plumbing Tax (Cloud hosting, edge compute, serverless databases)
3. The Trust Tax (Identity verification, cybersecurity, bot prevention)
4. The Habit Tax (Lifecycle marketing, SMS/email APIs, CRM)

# MODULE 2: THE TOLLBOOTH WATCHLIST & PRIVATE THREATS
Translate the "Growth Tax" map into a ranked watchlist of 15-20 public companies. Filter explicitly for B2B SaaS, API-first architecture, and strong Product-Led Growth (PLG) motions. For EACH ticker, provide:
- The Direct Causal Link: Explain the exact mechanism of how 10,000 new AI-generated apps launching this month translates to fractional revenue for them.
- Private Market Threat Level: Who is the biggest [PRIVATE] competitor attacking this exact same spend, and how does it impact the public company's moat?
- Pricing Elasticity: Prioritize usage-based models (e.g., per API call, per gigabyte).
- KPIs to Track: 3 specific metrics to watch in their next 10-Q.

# MODULE 3: THE EXTINCTION LIST (SHORTS & LOSERS)
Identify 5 public companies or sub-sectors that face severe margin compression or obsolescence because of this shift (e.g., legacy IT body shops selling billable coding hours). Explain the mechanism of their decline and what would invalidate this bear thesis.

# MODULE 4: THE CHAOS VARIABLES (SECOND-ORDER EFFECTS)
Identify 5 second- and third-order macroeconomic side-effects of this trend. For example:
- Will ad CAC (Customer Acquisition Cost) skyrocket due to infinite app supply bidding on finite human attention?
- Will the surge in automated apps trigger a massive spike in cyber-fraud, driving mandatory spend in Zero Trust security?

# STRICT EXCLUSIONS (WHAT NOT TO DO)
- Do NOT use vague corporate buzzwords (e.g., "synergies," "digital transformation") without explaining the exact mechanical revenue link.
- Do NOT include companies that rely primarily on one-off enterprise software licenses; focus only on recurring, volume-elastic, or usage-based pricing.
- Do NOT hallucinate metrics. If a specific KPI is unknown, state that it must be verified in the next earnings call.
- Do NOT provide generic retail investing disclaimers that waste space. Write this for an institutional portfolio manager.

# FINAL DELIVERABLES & FORMAT
Present the final output as a massive, highly detailed Institutional Research Memo (2,000+ words). 
1. Give full weight and depth to all 4 Modules. Do not summarize or shortcut the analysis.
2. Present the "Tollbooth Watchlist" (Module 2) in a highly scannable Markdown table.
3. Ensure every claim is backed by mechanical logic and testable KPIs.

Want to see exactly what this protocol generates?

View the full AI output here

Run that protocol. It will hand you a detailed, institutional-grade sector audit that Wall Street won’t price in for another six months.

If you want to stop relying on outdated DCF models and stay ahead of this curve, we are currently running exclusive services designed for serious practitioners. We offer mentorship programs on AI for product and market research, personalized 1-on-1 sessions, and access to our custom in-house tools.

We are also gearing up to launch GreekSoup.ai , an AI-based investment research tool like no other in the market, built specifically to give individual investors an institutional edge.

Go into the services section of our website to see how we can help you build your own robust investment frameworks.

https://shikshannivesh.com/services

Also wanted to share a bonus: I’m hosting a free 2-hour masterclass webinar on 15th Feb, “How to Research Any Industry from Scratch Using AI.”

You can check out the details and register here if interested: https://shikshannivesh.com/masterclass

Completely free. Live walkthrough. No slides. Recording if needed.

If already registered earlier this month, kindly ignore.

🤝 Help Us Grow This Circle

Share Alpha with AI

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

We believe investing should start with understanding and every newsletter we write is built to reflect that.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

“Anyone can build an LBO model. The spreadsheet doesn’t care who’s typing. But 90% of the models I’ve reviewed get thrown out in the first 60 seconds.”

That’s what a senior PE analyst told me two weeks ago.

I asked him why.

“Because they test the wrong things. The math is always fine. Excel doesn’t make arithmetic errors. But the assumptions? The debt sizing? The sensitivity variables That’s where you see who actually understands the deal and who just followed a template.”

That conversation is the reason this week’s workflow exists.

But let me back up.

I’m Shubham. I run Alpha with AI, a weekly newsletter where I build AI-powered workflows that replicate what institutional research teams do, and release them for free.

Every week, one workflow. Every workflow challenges an expensive industry standard.

I’ve built tools for earnings analysis, peer comparisons, insider trading detection. But this week, I tried something I’ve never done before.

I built an LBO modeling prompt.

The problem? I don’t build LBO models for a living. I’ve never worked in PE. Never sat across the table defending an IRR to someone with ₹500 Cr on the line.

So I did what any honest builder would do, I went to someone who has.

And what he taught me wasn’t the math.

It was the judgment.

That distinction<math vs. judgment> is the entire point of today’s newsletter.

Why most AI prompts for finance are useless

Here’s what most people do when they want AI to build a financial model:

They open ChatGPT. They type “Build me an LBO model. bla bla bla instructions in next few lines”

They get a clean-looking spreadsheet and they think it worked.

But here’s what actually happened, they got a template.

A structure. Rows and columns that look right. Numbers that don’t embarrass you at first glance. But try stress-testing it. Try changing one assumption and watching what breaks. Try showing it to someone who’s actually closed a leveraged deal.

It falls apart. Not because the math is wrong, but because nobody told the AI what to check. That’s the gap nobody talks about.

The AI can build a model in seconds. But it doesn’t know which assumptions to question. It doesn’t know that a 7x debt/EBITDA on a mid-cap industrial company is insane. It doesn’t know that your sensitivity table is testing variables that don’t actually move the deal.

The senior analyst I spoke to put it simply:

“A good model isn’t the one that runs. It’s the one that tells you when something doesn’t make sense.”

That one line rewired how I built this prompt. Because most AI finance prompts are instructions.

Do this. Calculate that. Format it like this.

This prompt is different. It’s not a set of instructions.

It’s a set of questions.

The 5 things the prompt checks that you wouldn't

Let me show you what this looks like in practice.

You open Excel. Three sheets of financial data, income statement, balance sheet, cash flow. Plus market cap and enterprise value.

You open Claude’s integration. It sits right inside Excel now. No browser tab. No copy-pasting. Just a chat window inside your spreadsheet.

You paste one prompt and then something happens that doesn’t happen with generic AI prompts.

It starts asking the right questions. Not “what font do you want for the header.”

The real questions. The ones that separate a model from a template.

Here’s what I mean:

1. It doesn’t guess your assumptions, it derives them.

Most AI prompts ask you to input assumptions manually.

Or worse, they make them up.

This prompt pulls Capex, D&A, and Net Working Capital ratios directly from your historical data. Three-year averages. Not vibes. Not industry benchmarks from a textbook. YOUR company’s actual numbers.

You can override them. But the starting point is real.

2. It checks if your deal structure makes sense.

Here’s where the analyst’s thinking shows up.

After sizing the debt, the prompt calculates implied Debt/EBITDA and surfaces it right next to your assumptions. Not buried in a formula somewhere.

Right there. Staring at you.

If you’re trying to lever a mid-cap company at 8x EBITDA, the model doesn’t stop you, but it makes sure you see what you’re doing.

That’s the difference between a tool and a teacher.

3. It stress-tests what actually matters.

Most sensitivity tables I’ve seen test variables that look impressive but don’t move the deal.

This prompt builds a 5×5 sensitivity grid around two things that actually determine whether a PE deal works: exit multiple and entry premium.

25 scenarios. Each one recalculates dynamically. Each one tells you something about the deal that a single IRR number never could.

4. It doesn’t hide the math.

Everything is formula-driven. Every output cell references an assumption cell. Nothing is hardcoded.

Change one assumption and watch the entire model ripple. That’s not just a feature, that’s how you learn what drives an LBO.

5. It runs on one tab. Inside Excel. In minutes.

No switching between tools. No exporting CSVs. No debugging Python scripts.

One tab called “LBO Analysis.” Summary box at the top.

Entry Equity, Exit Equity, MoM, IRR, all visible before you scroll.

The model that used to take days now takes a conversation.

But the prompt isn't the most important part.

The Prompt Isn’t the Alpha. This Is.

Here’s what nobody tells you about using AI for financial modeling.

The prompt matters. But it’s not the difference-maker.

The context is.

Before I run this prompt, I add a sheet to the workbook. First sheet. Plain text. No formulas. Just context.

What sector the company operates in. What the competitive landscape looks like. Any thesis I have about revenue growth or margin expansion. What a PE buyer might care about for this specific business.

Why? Because Claude reads every sheet in the workbook before it responds.

So when it suggests a revenue CAGR or an exit multiple, it’s not pulling from generic defaults. It’s reasoning from YOUR context about THIS company. That’s the difference between a model that looks right and a model that thinks right.

The prompt gives Claude structure. The context sheet gives Claude judgment.

Add both. That’s the real workflow.

Watch. Then Judge.

Don’t take my word for it.

Watch.

That’s it. One prompt. One conversation inside Excel.

A full LBO model with institutional logic.

No editing. No manual adjustments. No switching between tools.

Just the raw output from a single prompt.

Now here’s what I want you to sit with for a moment.

I don’t have a PE background. I’ve never built LBO models professionally. I spent a few hours learning from someone who has and turned that conversation into a prompt.

And the prompt works.

Not because I’m special. Not because AI is magic. Because the real skill in finance was never the spreadsheet.

It was knowing what to look for inside the spreadsheet.

The assumptions that don’t make sense. The leverage ratio that’s too aggressive. The sensitivity variables that actually move the deal.

That knowledge used to live in one place, the heads of people who’d done it for 10, 15, 20 years.

Now it lives in a prompt. That’s not a threat to experienced analysts.

It’s a shift in where the value sits. The analyst who taught me didn’t feel threatened.

He was fascinated. Because he realized something:

His 15 years of judgment, the pattern recognition, the instinct for what looks wrong, the questions he asks before anyone else thinks to ask them, that can now be encoded. Shared. Scaled.

The mechanical work? AI handles that.

The judgment? That’s still human. But it’s no longer locked inside one person’s head.

That’s what Alpha with AI is about.

Not replacing analysts. Democratizing the judgment that used to take a decade to develop.

One workflow at a time.

Here’s the full prompt:

You are a senior private equity analyst building an LBO model. Before you begin, read every sheet in this workbook carefully — financial statements, market data, and any 
context or investment thesis notes provided.

Your task: Construct a complete Leveraged Buyout analysis based on the historical financial data in this workbook (3 years of income statement, balance sheet, and cash flow statement, plus current market cap and enterprise value).

If a context sheet exists with sector information, competitive positioning, or investment thesis notes — use that to inform your assumption choices and flag anything in the data that contradicts or supports the thesis.

---

## 1. ASSUMPTIONS

### User-Adjustable Assumptions
Recommend starting values based on the company's historical performance, sector context, and current market conditions. 
For each assumption, include a brief note explaining your reasoning:

- Purchase premium over current market cap (%)
- Debt / Equity split for acquisition financing (display implied Debt / LTM EBITDA as a sanity check)
- Interest rate on acquisition debt (%)
- Revenue CAGR across the 5-year hold period (%)
- EBITDA margin at exit (% — note whether this assumes expansion or contraction vs. current margin, and why)
- Exit multiple (x LTM EBITDA at Year 5)

### Derived Assumptions (lock from historical data)
Calculate these directly from the financials — do not estimate or assume generic benchmarks:

- Capex as % of revenue → 3-year historical average
- D&A as % of revenue → 3-year historical average
- Net Working Capital as % of revenue → most recent year (NWC = Current Assets excl. Cash − Current Liabilities excl. Debt)
- Tax rate: 21%
- Hold period: 5 years
- Debt repayment structure: bullet repayment at exit (no annual amortization — FCF accumulates as cash on balance sheet throughout the hold)

### Assumption Sanity Check
After setting assumptions, flag any of the following:
- Debt/EBITDA above 6.0x (aggressive for most sectors)
- Exit multiple significantly above entry implied multiple
- Revenue CAGR that deviates sharply from historical trend
- EBITDA margin assumption that contradicts sector dynamics or context provided

---

## 2. SOURCES & USES

Uses:
- Purchase equity value (current market cap × (1 + premium))
- Refinance existing net debt (from balance sheet)
- Transaction fees: 1.5% of enterprise value
- Financing fees: 2.0% of new debt raised

Sources:
- New acquisition debt (sized to target Debt/Equity ratio)
- Sponsor equity contribution (plug to balance)

Verify: Total Sources = Total Uses
Display: Implied Debt / LTM EBITDA from debt quantum

---

## 3. FINANCIAL PROJECTIONS

Layout: 2 historical years + 5 projection years (columns)

Row items:
- Revenue
- Revenue growth (%)
- EBITDA
- EBITDA margin (%)
- Depreciation & Amortization
- EBIT
- Interest expense (Entry Debt × Interest Rate — constant debt balance until exit)
- EBT (Earnings Before Tax)
- Taxes
- Net Income
- Capital Expenditures
- Change in Net Working Capital
- Levered Free Cash Flow (Net Income + D&A − Capex − Change in NWC)
- Cumulative Free Cash Flow

---

## 4. RETURNS ANALYSIS

Calculate:
- Exit Enterprise Value = Year 5 EBITDA × Exit Multiple
- Ending Net Debt = Entry Debt − Cumulative FCF
- Exit Equity Value = Exit EV − Ending Net Debt
- Entry Equity = Sponsor equity from Sources & Uses
- Money-on-Money (MoM) = Exit Equity ÷ Entry Equity
- IRR = 5-year IRR 
  (Year 0 outflow: Entry Equity → Year 5 inflow:Exit Equity)

---

## 5. SENSITIVITY TABLE

Build a 5×5 grid showing IRR across:
- Columns: Exit Multiple at base case ±1.0x and ±2.0x
- Rows: Entry Premium at base case ±10% and ±20%

Requirements:
- Use direct formulas, not Excel Data Tables
- Each cell must recalculate dynamically
- When entry premium changes, debt quantum adjusts proportionally to maintain the target Debt/Equity ratio
- Highlight the base case cell

---

## 6. DEAL ASSESSMENT

Add a brief commentary section below the sensitivity table:

- Does this deal achieve a minimum 2.0x MoM / 15% IRR at base case?
- What is the margin of safety — how much can exit multiple compress before returns fall below 2.0x?
- What are the 1-2 biggest risks to the return profile based on the numbers?
- If context/thesis was provided: does the model support or challenge the investment thesis?

---

## FORMATTING

- Build everything on a single new tab: "LBO Analysis"
- Each section as a clearly labeled, separated table
- Years in columns, metrics in rows
- Assumption cells: blue font with cell borders (clearly marked as editable inputs)
- Derived/calculated cells: black font (clearly distinguished from inputs)
- Summary box at the very top of the tab showing:
  Entry Equity | Exit Equity | MoM | IRR
- All outputs must be formula-driven, referencing assumption cells — no hardcoded values anywhere

How to use it:

1. Open an Excel workbook with 3 years of financials (income statement, balance sheet, cash flow) plus current market cap and enterprise value and most important part, don’t forget to add context in the first sheet itself.

2. Open Claude integration inside Excel (requires Claude Pro: $20/month)

Add in Process:

1. Navigate to the Claude in Excel listing on Microsoft Marketplace.

2. Click “Get it now” to install the add-in.

3. Open Excel, activate the add-in, and sign in with your Claude account.

Claude in Excel accelerates spreadsheet work through intelligent assistance. It reads complex multi-tab workbooks, explains calculations with cell-level citations, and safely updates assumptions while preserving formula dependencies. Create pivot tables and charts to visualize your data, or upload files directly into your workflow.

Whether you're debugging errors, building new models, or modifying existing ones, Claude maintains full transparency by tracking changes and providing clear explanations at every step.

3. Paste the prompt

4. Review the output. Adjust the assumptions. Stress-test the sensitivity table.

That last step is the important one. The model gives you answers. Your job is to question them.

That’s how an analyst thinks.

Remember what the analyst said?

“90% of the models I’ve reviewed get thrown out in the first 60 seconds.”

Not because the math was wrong. Because nobody asked the right questions.

This prompt asks the right questions. Not because I figured them out, because someone with 15 years of deal experience told me what they were.

I just made sure AI remembers them every single time.

That’s the bet I’m making with Alpha with AI.

Every week, I find someone who’s spent years building judgment in their field. I learn what they know and I encode it into a workflow that anyone can use.

Not theory. Not courses. Not paywalled research.

Free tools that think like practitioners.

This week it was LBO modeling. Next week it’ll be something else. The library keeps growing.

Now here’s what I want you to do.

Don’t just save this prompt. Run it. Pull up any company’s financials. Paste the prompt. Read the output.

Then question it. Check the assumptions. Push back on the leverage ratio. Ask yourself if the exit multiple makes sense.

That’s not AI replacing your thinking. That’s AI giving you something worth thinking about.

See you next Sunday.

(Launching on 20th Feb)

The SuperAnalyst Mentorship (12-Week Cohort)

The Research Stack I shared today is just one gear in a much larger engine.

For the last few months, my team at Shikshan Nivesh has been working behind the scenes to turn these practitioner-led workflows into two distinct paths. We don’t do theory. We don’t do “guru” lectures. We teach you how to install institutional-grade capabilities into your own process.

Explore SuperAnalyst Mentorship

We recently launched the Super Analyst Mentorship, a hands-on program for anyone who wants to learn how to build AI workflows like this one from scratch.

Not just using prompts. Building them. Thinking like an AI architect.

If that’s you → check out the details on our website services module: https://www.shikshannivesh.com/

Also wanted to share a bonus:

I'm hosting a free 2-hour masterclass webinar on 7th Feb, "How to Research Any Industry from Scratch Using AI."

Live walkthrough. No slides. Recording if needed.

You can check out the details and sign up here if interested: https://topmate.io/shubhamborkar
Completely free.

🤝 Help Us Grow This Circle

Share Alpha with AI

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

The “Analyst” Fallacy

I used to spend my Friday nights doing something painful.

I would scroll through hundreds of rows of raw regulatory filings, page after page of transaction data.

I was looking for one thing: Conviction.

See, an analyst can upgrade a stock because their boss told them to. A TV pundit can pump a stock because they need ratings. That information is cheap.

But a CEO? They don’t buy their own stock by accident. When a CFO reaches into their own pocket, that is the only “Strong Buy” rating that actually has skin in the game.

But here was the problem.

Finding that signal manually is a nightmare. It’s not just boring; it’s dangerously inefficient.

I was downloading CSVs, filtering out thousands of “0-value” ESOP exercises, and Googling director names just to see if they mattered.

Sure, you can analyse this into Excel or write a Python script to scrape it. But then you’re still spending your time cleaning data, fixing formats and mapping columns, instead of interpreting it.

I was spending 90% of my time acting like a human database and only 10% actually analyzing the trade.

I realized I wasn’t losing money because of bad analysis. I was losing money because manual research is too slow.

The “Speed” Edge

In 2026, information is a commodity. Insight is expensive. But speed is the only real edge left.

If it takes you 4 hours to download the data, clean the Excel sheet, and spot the trade, you are already late. The algos have priced it in.

The institutional desks aren’t scrolling. They have systems that flag these moves instantly.

I realized that if I wanted to compete, I didn’t need a better spreadsheet. I needed a pattern recognition engine.

I needed something that could look at a mess of data and instantly spot the difference between a “routine buy” and a “screaming signal.” Something that could connect the dots between a stock dropping 15% and a Promoter stepping in to buy the dip.

So, I built an workflow to do exactly that.

The "Insider Audit" Framework

Most people treat insider data as binary: “Buying = Good.”

My framework treats it as contextual. You don’t need more data; you need interpretation.

I didn’t just ask the AI to “find buys.” I programmed it with a Behavioral Conviction Framework to filter out the noise and score every transaction based on two “Conviction Multipliers”:

• Role Weighting: A buy from a CFO or CEO is weighted higher than a Director. They know the numbers best.

• The Cluster Rule: One insider buying is a data point. Three insiders buying in a 30-day window is a “Wolf Pack.” That is coordinated conviction.

The agent reads the raw filings, applies this scoring logic, and translates the data into three clear, plain-English signals:

1. The Contrarian Buy (The “Dip” Signal)

• The Logic: Clustered buying after a stock has dropped 10–30%.

• The Translation: “The market is wrong about this drop. We are undervalued.”

2. The Momentum Confidence (The “Breakout” Signal)

• The Logic: Insiders buying into strength or near 52-week highs.

• The Translation: “This rally has legs. We expect the top to be much higher.”

3. The Risk Signal (The “Caution” Flag)

• The Logic: Insiders selling into euphoria or overbought conditions.

• The Translation: “We are taking chips off the table.”

The Workflow (Steal This)

I have created two versions of this agent: one for the Indian market and one for Global (U.S.) markets.

You don’t need to code. You just need to copy-paste.

The Setup:

1. Login: Go to Claude.ai (or ChatGPT).

2. New Chat: Start a fresh session. (Recommended but not required: Upload the Insider filings.)

3. Download Insider filings from here: NSE | BSE | Finviz

4. Paste: Copy the prompt below (choose your edition) and hit run.

(Note: The prompt contains embedded source links, so it can often retrieve data automatically. But I will suggest manual validation for hallucination free results, download the filings directly here: NSE | BSE | Finviz)

📺 Watch the Demo

If you want to see exactly how I run this in real-time, watch the full 4-minute walkthrough below.

Watch Demo

And if you want to see what a “perfect” run looks like, here is the live dashboard output from this week:

View Output

📋 The Prompt Kit

Copy the relevant version below and paste it into your AI workspace.

Option 1: India Edition (NSE/BSE)

INSIDER TRADING DASHBOARD — INDIA EDITION

You are an autonomous financial research agent equipped with browsing and reasoning capabilities.
Act as a buy-side analyst at an Indian equity fund tasked by your Portfolio Manager (PM) to identify and interpret insider conviction signals using insider transaction disclosures filed under SEBI (Prohibition of Insider Trading) Regulations, 2015, as available on NSE and BSE corporate filing portals.

Your mission:
Transform raw insider-trading disclosures into an actionable “Insider Conviction Dashboard” that reveals which companies’ promoters and executives are signaling genuine confidence or caution through recent open-market transactions.
Interpret data like a professional — emphasizing intent, clustering, and timing, not just frequency.

───────────────────────────────
INTERNAL RESEARCH PROCESS (DO NOT OUTPUT THESE STEPS)

Step 1 — Retrieve Insider Data
Access:
• NSE Corporate Filings – Insider Trading: https://www.nseindia.com/companies-listing/corporate-filings-insider-trading
• BSE Corporate Filings – Insider Trading: https://www.bseindia.com/corporates/Insider_Trading_new.aspx
Collect all insider transactions disclosed during the past 7 days.
For each record extract internally:
- Ticker / Company Name
- Insider name and designation (Promoter, MD, CEO, CFO, Director, KMP, Relative)
- Date of transaction
- Type – Acquisition / Disposal / Pledge / Revocation / ESOP
- Number of shares and total market value (₹ crore / lakh)
- Average transaction price
- Nature – Open-market, Block, Inter-se, Off-market, ESOP, Pledge related
- Repetition pattern by insider or promoter group

───────────────────────────────
Step 2 — Evaluate Conviction Strength

Assign a Conviction Score to measure insider intent:

Conviction Level | Criteria | Score
High | Open-market buy by Promoter / MD / CEO / Chairman exceeding ₹50 lakh | 3
Moderate | Open-market buy by CFO / Director / KMP of any size | 2
Low | ESOP exercise, automatic sale, pledge revocation/creation, or routine small transactions | 1

Rules of thumb:
• Focus on buys, not sales.
• Ignore tiny buys (<₹1 lakh) unless part of a cluster.
• If multiple insiders or promoter-group members buy within a 30-day window, raise average conviction by +0.5.
• Promoter pledge revocation = mildly bullish (+0.3), pledge creation = bearish (–0.3).

───────────────────────────────
Step 3 — Aggregate by Company

Group records by company ticker/name to identify conviction patterns.
For each company compute:
• Count of High-Conviction Buys (Score 3)
• Total number of distinct insider buyers
• Flag Promoter/CEO/CFO involvement
• Total ₹ value of all Buys (30 days)
• Presence of pledging/revocation events
Rank companies by conviction intensity (weight seniority + cluster size + value).

───────────────────────────────
Step 4 — Add Price & Sentiment Overlay

For top 10 tickers open their NSE/BSE quote pages or aggregators (Trendlyne, Screener). Extract:
• 1M / 3M price trend (% change)
• Relative strength (rising / consolidating / under pressure)
• Recent company or sector news (Economic Times, Mint, BQ Prime)
• Analyst/Street tone (bullish / cautious / neutral)

Classify tone:
• Contrarian Setup: Buying into weakness or bad news
• Momentum Confidence: Buying into strength / new highs
• Risk Signal: Selling into overbought conditions
• Balance-Sheet Signal: Pledge revocation = cleanup confidence

───────────────────────────────
Step 5 — Behavioral Classification

Signal Type | Description | Interpretation
Contrarian Buy Signal | Clustered promoter/KMP buying after stock correction | Undervaluation / turnaround confidence
Momentum Confidence | Insider buying amid strength / sector rally | Reinforces bullish narrative
Risk Signal | Insider selling or pledge creation into strength | Caution / profit-taking
Governance Signal | CFO/Director buying in uncertain phase | Insider faith in governance / cleanup effort

───────────────────────────────
Step 6 — Sector & Macro Context

Analyse patterns:
• Which sectors show buying concentration?
• Which sectors show selling or pledging pressure?
• Are insiders buying post-corrections or selling rallies?
• Does the pattern fit a risk-on (domestic demand, capex) or risk-off (defensive, profit-taking) macro phase?

───────────────────────────────
FINAL OUTPUT FORMAT

Produce a single polished markdown report with the following sections:

───────────────────────────────
EXECUTIVE SUMMARY
Write 5 sentences highlighting:
• Key conviction themes across the Indian market
• Sector skew and concentration
• Behavioral patterns (contrarian vs momentum vs pledge signals)
• Macro implications (domestic vs export orientation, risk-on vs risk-off)
• Overall insider sentiment tone

───────────────────────────────
TOP 10 CONVICTION DASHBOARD

Columns:
Rank | Company | Total ₹ Value (30 d) | # of Insiders | Promoter/CEO Involved | Avg Conviction Score | Signal Type | Comment
Sort by conviction intensity (weight seniority + cluster size + total value).

───────────────────────────────
COMPANY-LEVEL NARRATIVE INSIGHTS

For each of the top 10 companies, write 2–3 sentences explaining:
• Who bought/sold and their designation
• Price context (buying weakness vs strength)
• What it signals about insider conviction
• How it relates to recent company events or sector tone

Example:
KEI Industries: Promoter group acquired ₹2.8 Cr worth of shares in the open market after a 12% drop post-Q2 results. Indicates confidence in long-term order book growth despite margin compression headlines. Clustered buying by family members strengthens signal of genuine conviction.

───────────────────────────────
SECTOR & MACRO PATTERNS

Summarize 3–5 sentences:
• Sectors showing buying concentration (e.g., Capital Goods, PSU Banks)
• Sectors with sales/pledge pressure (e.g., IT, Pharma)
• Implications for macro regime (risk-on vs risk-off)
• Link to policy backdrop (infra push, credit cycle, Make in India)

───────────────────────────────
KEY TAKEAWAYS
Provide 3 actionable investor insights, e.g.:
• Clustered promoter buying in industrials = domestic capex confidence
• Tech selling into strength = rotational caution
• Pledge revocations rising = balance-sheet cleanup theme

───────────────────────────────
DISCLAIMER
This is an educational initiative for investor awareness and does not constitute investment advice.

───────────────────────────────
STYLE & OUTPUT GUIDELINES
• Tone: professional buy-side morning note — analytical and concise.
• Use Indian ₹ values and sector terminology.
• Avoid jargon unless standard in equity research.
• Highlight intent and timing over transaction count.
• Always link insider actions to price and macro cycle.
• Do not list raw filings or names without interpretation.

Option 2: Global Edition (Finviz/SEC)

INSIDER TRADING DASHBOARD - GLOBAL EDITION
# GOAL
You are an autonomous financial research analyst working under a Portfolio Manager (PM).
Your job is to track and interpret insider activity using public data from Finviz — specifically, recent Form 4 filings.

Your mission:
Transform Finviz’s insider-trading listings into an actionable “Insider Conviction Dashboard” that reveals where company insiders are showing genuine confidence or caution through their recent trades.

You must think and write like a professional analyst — emphasizing intent, timing, and clustering, not just frequency or dollar size.

---

## INSTRUCTIONS

### Internal Research Process (Do Not Output These Steps)

**Step 1 — Retrieve Insider Data**
Go to **https://finviz.com/insidertrading.ashx**
Collect insider transactions from the past 7 days.

For each transaction, extract:
- Ticker
- Insider name and designation (e.g., CEO, CFO, Director)
- Transaction date
- Transaction type (Buy or Sale)
- Number of shares and total dollar value
- Transaction price
- Classification (Purchase, Sale, or Option exercise)
- Any repeat patterns by insider or company

---

**Step 2 — Evaluate Conviction Strength**

Assign a Conviction Score to each trade based on intent and significance:

| Conviction Level | Criteria | Score |
|------------------|----------|-------|
| High | Open-market buy by CEO, CFO or Chairman above $100 K | 3 |
| Moderate | Open-market buy by other senior officers or directors (any size) | 2 |
| Low | Option exercise / automatic sale / routine disposition | 1 |

**Guidelines:**
- Focus on Buys, not Sales.
- Ignore token purchases (< $10 K) unless they form a cluster.
- Multiple insiders buying the same company = stronger signal of conviction.

---

**Step 3 — Aggregate by Company**

Group transactions by ticker to identify patterns of confidence.

For each company:
- Count High-Conviction Buys (Score 3)
- Count distinct insider buyers
- Flag CEO / CFO involvement
- Sum total dollar value of all Buys (30 days)
- Compare to historical Finviz data if available

Rank companies by overall insider-conviction intensity, weighting both seniority and cluster size.

---

**Step 4 — Add Price & Sentiment Context**

For the top 10 tickers, open their Finviz quote pages (e.g., https://finviz.com/quote.ashx?t=TICKER).
Capture:
- 1-month / 3-month price trend
- Relative strength (rising, flat, or under pressure)
- Recent headlines and analyst sentiment

Classify tone:
- **Contrarian Setup:** Insiders buying into weakness / negative news
- **Momentum Confidence:** Insiders buying into strength / uptrend
- **Risk Signal:** Insiders selling into overbought conditions

---

**Step 5 — Behavioral Classification**

| Signal Type | Description | Interpretation |
|--------------|--------------|----------------|
| Contrarian Buy Signal | Clustered buying after price weakness | Management expects recovery / undervaluation |
| Momentum Confidence | Buying during strength | Reinforces bullish narrative |
| Risk Signal | Selling into strength | Caution / profit-taking |

---

**Step 6 — Sector & Macro View**

Look for broader behavioral themes:
- Which sectors show buying clusters?
- Which show persistent selling?
- Are insiders buying the dip or selling the rally?
- What does this imply about macro risk sentiment (risk-on vs risk-off)?

---

## FINAL OUTPUT FORMAT

After completing your research, produce a single markdown report with the following structure:

### Executive Summary
Write 5 sentences that capture:
- Key conviction themes in the past week
- Sector skew and clustering
- Behavioral patterns (contrarian vs momentum)
- Macro implications
- Overall insider sentiment tone

---

### Top 10 Conviction Dashboard

| Rank | Ticker | Total $ Value | # of Insiders | CEO/CFO Involved | Avg Score | Signal Type | Comment |
|------|--------|---------------|---------------|------------------|-----------|-------------|---------|
| 1 | XYZ | $2.4 M | 3 | Yes | 2.8 | Contrarian Buy | Clustered buying post-earnings drop |
| 2 | ABC | $0.9 M | 2 | No | 2.3 | Momentum Confidence | Director buying after 20 % pullback |

---

### Company-Level Narrative Insights
For each of the top 10 names, write 2–3 sentences covering:
- Who bought / sold and their role
- Price context (weakness vs strength)
- What it signals about insider intent
- Recent company events or sentiment

**Example:**
**XYZ Corp:** CEO and CFO each purchased ≈ $500 K after a 15 % post-earnings sell-off. Signals internal confidence that the weakness is temporary. Stock is near 12-month lows with improving fundamentals — a classic contrarian setup.

---

### Sector & Macro Patterns
Summarize cross-sector behavior:
- Where is buying concentrated?
- Where is selling emerging?
- Are insiders adding risk or reducing exposure?
- What macro tone does this suggest?

Write 3–5 sentences linking insider behavior to broader market themes.
*Example:* Heavy buying in Financials and Industrials signals soft-landing confidence, while Tech insider selling points to profit-taking in crowded AI trades.

---

### Key Takeaways
End with 3 concise, actionable insights:
- Clustered buying in small/mid-cap industrials = early-cycle confidence
- Tech insiders selling into strength = sentiment excess
- Financials showing accumulation = quiet re-risking trend

---

## STYLE GUIDELINES
- Write like a PM’s morning note — clear, analytical, no fluff.
- Focus on intent and timing over volume.
- Use markdown tables and bold key phrases.
- Offer interpretation, not data dumping.
- Highlight where insider behavior contradicts consensus.
- Output only the final report sections above — no intermediate steps.

The Final Word

In 2026, information is cheap. Insight is expensive.

If you are still manually reading filings, you are competing on “effort.” That’s a losing game. The goal of Alpha with AI is to help you compete on “judgment.”

Let the AI do the reading. You make the trade.

The Alpha Installation (Launching on 20th Feb)

The Research Stack I shared today is just one gear in a much larger engine.

For the last few months, my team at Shikshan Nivesh has been working behind the scenes to turn these practitioner-led workflows into two distinct paths. We don’t do theory. We don’t do “guru” lectures. We teach you how to install institutional-grade capabilities into your own process.

We are now opening Expressions of Interest for our Q1 2026 intake:

1. The SuperAnalyst Mentorship (12-Week Cohort)

For analysts, investors, consultants, and ambitious researchers. This is a deep-dive into the modern financial research stack. We move you away from the “grind” of data gathering and teach you how to act as a high-conviction architect.

• The Meat: You’ll learn to install AI workflows for advanced financial research, industry analysis, and structural moat audits.

• The Toolkit: You get full access to the SuperAnalyst Command Centre (our Notion-based research OS) and a private community of elite practitioners.

• Investment: ₹49,000 (12-week intensive).

2. Idea to Launch: AI-Powered Consultation

For founders and professionals turning ideas into validated products. This isn’t a service where we build for you. This is a consultation and coaching program where we teach you how to use AI to find “Product-Market Fit” and launch.

• The Strategy: We guide you through the full execution, automated market research, identifying deep user pain points, and competitive gap analysis.

• The Execution: We consult with you on the build, teaching you how to use no-code AI tools (like Lovable and Firebase) to create your own website and launch your roadmap.

• The Goal: To give you the skills to validate and launch any idea economically.

• Investment: Starts at ₹9,999.

How to Express Interest

We are launching both programs in the next 30 days. Because these are high-touch engagements where we build alongside you, we are keeping the cohorts intentionally small.

If you want to be part of the Q1 intake:

[Reply to this email with “GROWTH” and tell me which program interests you.]

My team and I will reach out directly to see if your goals align with our practitioner-led approach.

🤝 Help Us Grow This Circle

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

Share Alpha with AI

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

Because the future of analysis isn’t about who knows Excel best.

It’s about who builds thinking systems that scale.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Guide & Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

I used to think that being a “Top Advisor” was about how much data I could handle.

I spent years believing that the more research reports I read, the better my advice would be.

At the time, I was managing and advising on significant HNI portfolios. The pressure was high. My clients wanted answers on thousands of different stocks, and my solution was always the same: Read more.

At that level, you aren’t the one building the 30-tab financial models. You are the one who has to make sense of them.

My research team would hand me a stack of reports on 300 different companies. They spent weeks on the assumptions, the DCFs, and the price targets.

But I only had 30 minutes to decide if their “conviction” was real or just accounting noise.

I was proud of the “grind.” I thought the solution to finding alpha was to read more reports, track more price targets, and dig deeper into my team’s assumptions.

But I was trapped in the “Hardworking Executive” cycle.

I was trying to achieve more by doing even more.

One afternoon, I hit a wall.

I was staring at a sector with dozens of “Buy” ratings from my team, trying to find just one high-conviction “Moat” that would actually survive a 2-year downturn.

I had 10 terminal windows open, 5 reports half-read, and zero clarity.

I realized I wasn’t being wise. I was just being busy.

In the age of AI, the hardworking person drowns because they use technology to “summarize more.”

The wise person wins because they use technology to eliminate more.

A wise researcher doesn’t look for more data to support a story. They look for the 90% of institutional noise they can safely ignore so they can focus on the 10% of structural truth.

I had to stop “deciding” on stories and start “filtering” for Economic DNA.

The Signal and the Noise

Most investors look at a high-growth market and think the hard part is over.

They believe that if they just follow the “Buy” ratings in a 20-page PDF from a research team, their capital is safe.

But they are looking at the wrong side of the ledger.

In 2026, P/E ratios and revenue targets are just “table stakes.” They are noise.

The real alpha is hidden in Capital Intensity, the structural DNA of how a business actually converts that growth into cash.

Traditional research coverage is dying because it is too slow to catch these nuances.

If you are a Senior Researcher, you know the truth: Most analysts spend weeks building beautiful models, but they miss the moment a Moat begins to leak because they are drowned in their own data.

Whether you are looking at the NSE or the NYSE, the reality is the same:

If you are still relying on human-only summaries to understand a business model, you are fighting a 2018 war in a 2026 market.

To protect your capital and the integrity of your research thesis, you don’t need a team of 50 people making more assumptions.

You need an elimination tool for decision-makers who don’t have the time to be factory workers.

You need a way to audit the structural quality of an entire sector in minutes, not weeks.

You need to move past “what the model says” and find the Economic DNA.

The 3-Step Selection SOP

To move from “Data Noise” to “Institutional Insight,” I use a three-step funnel.

The goal isn’t just to find a “Buy” rating. The goal is to eliminate 95% of the market so you can focus your intellectual capital on the 5% that actually matters.

Step 1: The Macro Filter (The “Why Now?”)

Before looking at a ticker, you must look at the structural environment. A wise researcher identifies the “Growth Pillars” that have government tailwinds or massive capital shifts.

• Example Case Study (India): Right now, we see structural shifts in Digital Infrastructure and High-End Manufacturing. These aren’t just “trends”, they are foundational changes in the economy.

• The Goal: Eliminate sectors where growth is cyclical (temporary) and focus on where it is structural (long-term).

• The Methodology: I recently shared a full framework on Using AI for Industry Research that helps you automate this macro filtering process in minutes.

  

Step 2: The Selection Logic (The Input Filter)

This is where you move from the "Factory Worker" mindset to the "Architect" mindset. You have a sector, but how do you pick the 3 companies for your watchlist? I use a High-Conviction Filter to arrive at the right input:

1. Market Dominance: Is the company a top-5 player in its specific niche?

2. Moat Directionality: Is their competitive advantage expanding (e.g., through proprietary tech or scale) or shrinking?

3. Cash Conversion: Does their “accounting profit” actually turn into “free cash flow”?

If a company doesn’t pass these three filters, it doesn’t even make it to my AI audit. We eliminate them early.

Step 3: The Grounded Institutional Audit

Once you have your 3 shortlisted companies, you move to the execution phase.

Instead of reading 300-page reports manually, we feed the official raw data (Annual Reports, Investor Presentations, brokerage reports, last 1-2 year earnings transcripts) into a Grounded AI environment (like NotebookLM).

This allows the AI to act as a Senior Analyst that:

• Extracts only verified facts (No hallucinations).

• Audits the Economic DNA of the business.

• Separates management “marketing speak” from the structural reality.

Institutional Audits at AI Speed

The biggest problem with traditional research is the “Marketing Gap.” Management teams spend millions on investor presentations designed to make every business look like a “once-in-a-lifetime” opportunity.

If you or your team are reading those reports manually, you are subconsciously being sold a story.

My AI workflow is designed to break that story.

By using a Grounded “Source-Only” constraint, the AI ignores the glossy photos and the optimistic adjectives. Instead, it audits the Economic DNA hidden in the fine print.

The 2,000-Word Deep-Dive

What used to take a junior analyst 3 days to draft and a Senior Lead 30 minutes to verify, is now ready in under 10 minutes. The output is a comprehensive, institutional-grade audit that focuses on three non-negotiable pillars:

1. Moat Durability: It doesn’t just list “Competitive Advantages.” It audits if those advantages are structurally expanding or being eroded by new market entrants.

2. Capital Intensity: It separates accounting profit from economic reality. If a business needs ₹5 of Capex to generate ₹1 of growth, the AI flags it as a “Low-Alpha” trap.

3. Management Integrity: It cross-references management’s previous promises against current results, identifying where the “marketing speak” deviates from the data.

The result? A 2,000-word report that is ready for a Head of Research or a Lead Portfolio Manager to review immediately.

You move from “Gathering Data” to “Making Decisions” in the time it takes to grab a coffee.

Build Your Own Research Stack

The elite researchers of 2026 aren’t the ones reading the most pages.

They are the ones building the frameworks to synthesize them.

If you want to stop drowning in “institutional noise” and start leading with “structural truth,” it’s time to upgrade your research stack.

You don’t need a bigger team. You need a better filter.

Want to use this exact workflow for your next research project?

The “Senior Analyst” Audit Prompt

Copy and paste the following prompt once your data is uploaded. This is designed to act as an institutional-grade filter, not a summarizer.

### **The Master Alpha Prompt**

**System Persona:** You are a Senior Fundamental Investment Analyst 
specializing in Quality Investing and  (Return on Invested Capital) frameworks. Your goal is to perform a high-conviction "Economic Audit" of the business described in the sources.

**Task:** Analyze the provided sources to evaluate the company’s 
"Economic DNA." Do not summarize; provide a critical structural assessment.

**1. Economic Bottom Line & DNA:**

* Classify the business based on its structural DNA (e.g., Asset-light 
Compounder, Capital-Intensive Cyclical, or Toll-bridge Monopoly).
* Identify the **Revenue Engine**: What core 20% of products or services
 are driving 80% of the profits? Is growth coming from volume, price hikes,
 or new markets?

**2. ROIC & Capital Efficiency Audit:**

* Identify reported  or closest metrics. Distinguish between Tangible 
Capital and Goodwill.
* Analyze asset turnover and margin stability. Can this business grow 
earnings without a proportional increase in capital? Identify the 
"Cash Conversion" profile.
* **Incremental Unit Economics:** Calculate capital required per 
incremental unit of growth vs. the cash generated per mature unit.

**3. Strategic Moat Directionality:**

* Identify the primary Moat source: Pricing Power, Cost Advantage, 
Switching Costs, or Network Effects.
* Crucially, state if the Moat is **Expanding (Strengthening)** or 
**Infiltrated (Weakening)** based on competitive commentary and market share 
data in the sources.

**4. Forensic Management Audit (The Marketing Gap):**

* Locate management's specific outlook or promises from the previous year's
report. Cross-reference them against current results.
* Identify specific instances where "marketing speak" in the investor 
presentation deviates from the hard financial data in the official filings.

**5. Earnings Sustainability & Fragility:**

* Identify the **"Moat Leak"**: 3 structural risks that could break the 
investment thesis in the next 24 months.
* Evaluate industry structure and competitive pressure. Is there a high risk 
of "Mean Reversion"? Classify profitability as: Structural, Cyclical, or 
Temporary.

**6. Executive Synthesis:**

* Provide a final "Investment vs. Elimination" summary for a Lead Portfolio 
Manager.
* **Constraint:** If data for a section is missing, state "Data not present 
in official sources." Do not hallucinate based on general market knowledge.

1. Audit the Citations: In grounded environments like NotebookLM, always click the citations. Ensure the AI isn’t mistaking a CEO’s “ambition” for a historical fact.

2. Look for the “Moat Leak”: Focus 80% of your energy on Section 5 (Sustainability & Fragility). If the AI finds a structural risk that the mainstream research reports are ignoring, you have found your Alpha.

3. The Integrity Filter: Pay close attention to the Forensic Management Audit. If there is a recurring gap between management promises and capital reality, it doesn’t matter how high the ROIC is, the business is a “trap.”

This is the future of research: Using AI to do the “grind,” so you can do the “thinking.”

The Alpha Installation (Launching in 30 Days)

The Research Stack I shared today is just one gear in a much larger engine.

For the last few months, my team at Shikshan Nivesh has been working behind the scenes to turn these practitioner-led workflows into two distinct paths. We don’t do theory. We don’t do “guru” lectures. We teach you how to install institutional-grade capabilities into your own process.

We are now opening Expressions of Interest for our Q1 2026 intake:

1. The SuperAnalyst Mentorship (12-Week Cohort)

For analysts, investors, consultants, and ambitious researchers. This is a deep-dive into the modern financial research stack. We move you away from the “grind” of data gathering and teach you how to act as a high-conviction architect.

• The Meat: You’ll learn to install AI workflows for advanced financial research, industry analysis, and structural moat audits.

• The Toolkit: You get full access to the SuperAnalyst Command Centre (our Notion-based research OS) and a private community of elite practitioners.

• Investment: ₹TBD (12-week intensive).

2. Idea to Launch: AI-Powered Consultation

For founders and professionals turning ideas into validated products. This isn’t a service where we build for you. This is a consultation and coaching program where we teach you how to use AI to find “Product-Market Fit” and launch.

• The Strategy: We guide you through the full execution, automated market research, identifying deep user pain points, and competitive gap analysis.

• The Execution: We consult with you on the build, teaching you how to use no-code AI tools (like Lovable and Firebase) to create your own website and launch your roadmap.

• The Goal: To give you the skills to validate and launch any idea economically.

• Investment: Starts at ₹9,999.

How to Express Interest

We are launching both programs in the next 30 days. Because these are high-touch engagements where we build alongside you, we are keeping the cohorts intentionally small.

If you want to be part of the Q1 intake:

[Reply to this email with “GROWTH” and tell me which program interests you.]

My team and I will reach out directly to see if your goals align with our practitioner-led approach.

The P.S. Loop

P.S. Try this elimination mindset on your own research this week. Let me know the results or tell me what you think of this "Wise vs. Hardworking" shift, by replying directly to this email. I read every one.

P.P.S. Stay tuned for our next big drop: Quant with AI (Episode 1). We are deep-diving into a Claude-based workflow to analyse Insider Trades like an institution. If you want to know what the "smart money" is doing before the market reacts, you won't want to miss this.

🤝 Help Us Grow This Circle

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

Share Alpha with AI

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

Because the future of analysis isn’t about who knows Excel best.

It’s about who builds thinking systems that scale.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Guide & Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Last week, a senior research analyst reached out with a problem I didn’t expect.

He covers multiple sectors. Has done this for 20 years. The kind of analyst who’s seen enough cycles to smell trouble before it shows up in the numbers.

Yet here he was, stuck.

He wanted to initiate coverage on a new sector, one he’d never touched before. Not a hot sector with abundant sell-side research. Not something Bloomberg or Refinitiv had neatly packaged. A niche industry where the information was scattered across regulatory filings, trade body reports, and consultant PDFs buried three pages deep in Google searches.

“I need to initiate coverage on a sector I’ve never touched. The information is everywhere and nowhere. I don’t have three weeks.”

He wanted an AI system that could help. But not the usual kind.

Not one that confidently invents numbers. Not one that hallucinates trends. He wanted something he could actually trust, something that would cite its sources, admit when it didn’t know, and let him verify every claim.

So we built it.

And somewhere in the middle of that process, I realized, this isn’t his problem alone. This is every analyst entering unfamiliar territory. Every investor researching a sector before deploying capital. Every professional who’s ever stared at a new industry and thought: where do I even begin?

That’s when I decided to document everything and give it away for free.

What follows is the complete framework, the same system we built last week, refined and generalized so you can deploy it for any industry, in any geography, starting today.

The Problem with Industry Research Today

Let me describe what most people do when researching a new industry.

They open ChatGPT. Or Claude. Or Perplexity. They type something like: “Explain the specialty chemicals industry.” They get a confident, well-structured response. It sounds authoritative. The formatting is clean. The logic flows.

And that’s precisely the problem.

You have no idea which parts are real and which parts the model invented. That confident tone? It sounds the same whether the information is accurate or completely fabricated. The clean structure? It organizes facts and hallucinations with equal elegance.

I learned this the hard way.

Earlier in my career, I managed direct equity portfolios for some of India’s largest UHNI clients. In early 2024, I was researching a few small-cap names, looking for opportunities before the broader market caught on. I used AI to accelerate my research. Asked detailed questions about industry dynamics, competitive positioning, margin structures. Got confident, well-formatted answers. Built my conviction.

Then March happened.

The small-cap correction hit like a bloodbath. For a few brutal days, everything bled red. Now, corrections are part of the game, I’ve seen enough cycles to know that. But this time, something bothered me. I went back to revisit my original research. The facts I’d built my thesis on. The industry dynamics I thought I understood.

Many of those facts were completely fabricated.

Not wrong in interpretation. Fabricated. Statistics that didn’t exist. Relationships between variables that no source had ever documented. Citations that led nowhere.

We didn’t lose money, my clients were long-term investors, and the positions eventually recovered. But we lost something else. We lost opportunities. We sat on the sidelines for months, waiting for holdings to climb back, watching other ideas pass us by. All because I’d trusted AI outputs I couldn’t verify.

That experience changed how I think about AI in research.

The tools are powerful. But power without constraints is dangerous. For financial research, where a single wrong assumption can cascade into a flawed thesis, the AI needs to be tethered to verified sources. It needs to cite its work. It needs to say “I don’t know” when it doesn’t know.

That’s what we’re building today using NotebookLM.

Why NotebookLM (And Not Other AI Tools)

You might be wondering, why NotebookLM? Why not stick with ChatGPT or Claude or Perplexity? They’re faster. More conversational. Better at handling follow-up questions.

All true. And yet, for industry research, I don’t use them.

Here’s why.

NotebookLM does something other models can’t: it only answers from your uploaded sources. Every response comes with citations, page numbers, exact passages, verifiable references. When you ask it a question, it doesn’t draw from its training data. It doesn’t “know” things the way ChatGPT knows things. It searches through the documents you’ve given it and constructs answers based solely on that material.

This sounds like a limitation. It’s actually the entire point.

ChatGPT will answer any question you ask. Confidently. Fluently. Even when it’s making things up. Claude does the same. Perplexity adds citations, but those citations often don’t support the claims they’re attached to or worse, lead to pages that say something entirely different.

NotebookLM refuses to play that game. If the answer isn’t in your sources, it tells you. If a claim can’t be supported, it won’t make the claim. You lose the feeling of talking to an all-knowing oracle. You gain something far more valuable: trust.

The technical backbone:

NotebookLM runs on Gemini 3 with a full 1-million-token context window. You can upload up to 50 sources per notebook(on a free plan), hundreds of pages across annual reports, consultant studies, regulatory filings. All indexed. All searchable. All cited.

And it’s completely free. For users in India, Reliance Jio offers Google AI Pro free for 18 months through the Google AI Suite, unlocking additional features at no cost.

What NotebookLM won’t do:

It won’t access real-time information. It won’t update automatically when new reports release. It won’t connect to external databases or pull live market data.

But here’s the thing, for the kind of analysis we’re doing, you don’t need real-time. Industry structures don’t change overnight. Competitive dynamics evolve over years, not hours. The foundational research that helps you understand a sector deeply? That can be built once and updated periodically.

Real-time matters for trading. For understanding an industry? Depth matters more.

The Source Hierarchy: What to Feed Your Research Desk

Here’s something most people get wrong about AI-powered research: they focus on the tool and ignore the fuel.

You can have the most sophisticated system in the world. But if you’re feeding it garbage, you’ll get elegant garbage back. Formatted nicely. Cited properly. Still wrong.

Your analysis is only as good as your sources, and not all sources are created equal.

When I set up an industry research notebook, I follow a hierarchy. This isn’t arbitrary, it’s built from years of seeing what actually holds up when you dig deeper, and what falls apart under scrutiny.

Tier 1: Consultancy Reports

McKinsey. BCG. Bain. Deloitte. EY. KPMG. PwC. Accenture.

These firms produce some of the highest-quality industry research available. And here’s what most people don’t realize, much of it is free.

A former CXO client taught me this. When a company like Reliance or Tata wants to enter a new market, they pay these consultancies ₹2-5 Cr for a market entry study. The firm conducts rigorous primary research, surveys, expert interviews, proprietary data analysis, on-ground validation. Then, 6-12 months later, they publish a sanitised version as thought leadership content.

You’re getting 80% of the analytical value at 0% of the cost.

The trick is knowing where to find them:

• McKinsey Global Institute (mckinsey.com/mgi)

• BCG Henderson Institute (bcg.com/bcg-henderson-institute)

• Bain Insights (bain.com/insights)

• Deloitte Insights (deloitte.com/insights)

• EY Insights (ey.com/insights)

• World Economic Forum reports

• IMF and World Bank sector studies

Tier 2: Government and Regulatory Body Reports

This is where most people stop looking. That’s a mistake.

For niche industries like paper, textiles, leather, ceramics, specialty manufacturing, consultancy coverage is sparse. Wall Street doesn’t care. Bloomberg doesn’t package it neatly.

But these industries have their own knowledge infrastructure and it’s often deeper than what you’d find for mainstream sectors.

Every significant industry has a governing body. They exist because they need to lobby for policy changes, report to government, and coordinate industry standards. Which means they produce data. Lots of it. Annual reports. White papers. Market outlooks. Trade statistics.

Industry associations like the Indian Paper Manufacturers Association. Regulatory bodies like TRAI or SEBI or the Textile Committee. Export promotion councils. Chambers of commerce.

And here’s something even fewer people know: government ministries often commission research from agencies like CRISIL, ICRA, FICCI, or CII. These commissioned reports are rigorous, they inform policy decisions and they’re usually available free on ministry websites.

For global coverage, the same principle applies. UNIDO for manufacturing. FAO for agriculture. OECD for cross-country sector analysis. European Commission industry reports. US International Trade Commission studies.

The information exists. You just have to know where to look.

Tier 3: Company Annual Reports

Once you understand the industry landscape, you need to understand the players.

Annual reports are goldmines, but not for the reasons most people think. Yes, the financials matter. But the real value is in management commentary. Risk factor disclosures. Segment breakdowns. Capital allocation discussions.

Management teams are required to discuss what’s working and what isn’t. They have to disclose risks, competitive threats, regulatory headwinds, operational challenges. Read between the lines, and you’ll learn more about industry dynamics than any consultant report will tell you.

I typically upload 5-7 annual reports from the leading players in a sector. Not just the largest companies, but a mix that covers the full value chain. Upstream. Midstream. Downstream. Domestic leaders. Global competitors.

Tier 4: AI-Generated Deep Research

Only after I’ve gathered the primary sources do I use AI to fill gaps.

Gemini Deep Research. Perplexity. ChatGPT in research mode.

These tools are useful for synthesis, connecting dots, identifying themes you might have missed, generating questions you hadn’t thought to ask. But they’re supplements, not foundations.

Use them to identify what you don’t know. Then go find real sources to answer those questions.

The Source Discovery Framework

Building Your Source Library

Now comes the part where most people get stuck.

They know they need good sources. They understand the hierarchy. But when they actually sit down to build their research library, they spend hours clicking through websites, downloading PDFs one by one, getting lost in rabbit holes that lead nowhere.

There’s a faster way.

I use a systematic approach that combines AI-powered research with strategic manual sourcing. The goal is to build a comprehensive knowledge base in hours, not weeks, one that covers an industry from every angle.

The Three Pillars of Industry Understanding

Before you can analyze an industry intelligently, you need to understand three things:

1. How did we get here? — The historical forces that shaped the industry

2. Where is it going? — The growth drivers, constraints, and future scenarios

3. How does the money actually flow? — The operational mechanics and unit economics

I call these the Origin, Trajectory, and Engine of an industry. Miss any one of them, and your understanding has a blind spot.

To build this foundational knowledge, I use Gemini Deep Research to generate comprehensive reports on each pillar. Why Gemini specifically? It runs on Gemini 3 Pro, Google’s most factual model, specifically trained to reduce hallucinations during complex research tasks. It browses hundreds of websites, synthesizes information, and produces detailed, citation-backed reports.

A quick note: NotebookLM also has a Deep Research feature now, and you can use it if you prefer keeping everything in one place. It currently runs on Gemini 3 Flash, still powerful, but slightly less capable than Pro. Google has announced they’ll soon integrate the Gemini 3 Pro version into NotebookLM, so this gap will close. For now, I recommend using Gemini Deep Research for these foundational reports, then importing everything into NotebookLM for analysis.

The Workflow

1. Open Gemini (gemini.google.com)

2. Select “Deep Research” mode from the prompt bar

3. Paste each prompt below (one at a time)

4. Let it run, takes 3-5 minutes per report

5. Export each report as a google doc.

6. Import all three docs into your NotebookLM notebook

Let me share the exact prompts I use.

Prompt 1: Industry Origin (Historical Analysis)

ROLE
You are an economic historian and industry analyst specializing in [Industry Name] in [Country/Region].

OBJECTIVE
Create a comprehensive historical analysis (~ 10,000 words) that explains how this industry formed, evolved, and produced its current structure. Focus on cause-and-effect relationships and patterns that inform investment thinking.

RESEARCH FOCUS

1. Formation
- What problem or need created this industry?
- What were the first technologies, business models, and institutions?
- Who were the early pioneers and what advantages did they have?

2. Evolution & Expansion
- What breakthroughs enabled scale?
- How did costs, productivity, and barriers to entry change over time?
- When and how did the industry go from local to national to global?

3. Regulatory & Crisis Moments
- What major shocks reshaped the industry structure?
- How did government policy and regulation evolve?
- Which crises led to consolidation, and which opened doors for new entrants?

4. Competitive Dynamics
- How did winning companies build and sustain their edge?
- What caused once-dominant players to fail?
- What were the major turning points in market share?

5. Key Players Across Eras
- Who dominated in each major period?
- What drove leadership transitions?
- Which mergers, acquisitions, or breakups reshaped the landscape?

6. Modern Transformation
- How have digital technologies and automation changed the industry?
- What new business models have emerged in the last decade?
- How have margins and capital requirements shifted?

7. Regional Variations
- How do different geographies differ in industry structure?
- What role do trade policies, subsidies, and local regulations play?

8. Capital & Returns
- How has the industry been financed across different eras?
- What have returns looked like for investors over time?
- How has investor perception and valuation evolved?

OUTPUT REQUIREMENTS
- Use specific data, dates, and examples wherever possible
- Cite sources for key claims
- Identify recurring patterns that repeat across industry cycles
- Conclude with 5-7 key insights relevant for long-term investors

Prompt 2: Industry Trajectory (Growth & Future Outlook)

ROLE
You are an industry strategist and analyst specializing in [Industry Name] in [Country/Region].

OBJECTIVE
Create a forward-looking analysis (~ 10,000 words) that explains the current state, growth drivers, structural constraints, and plausible future scenarios for this industry. Focus on actionable insights for investors and business leaders.

RESEARCH FOCUS

1. Current State
- What is the market size, segmentation, and value chain structure?
- Where are the profit pools concentrated?
- Who are the key players and what are their market positions?
- What is the geographic distribution of demand and supply?

2. Growth Drivers
- What demand-side factors are driving growth? (demographics, consumption patterns, adoption curves)
- What supply-side factors are enabling expansion? (capacity additions, cost improvements, innovation)
- What policy or regulatory tailwinds exist?

3. Constraints & Headwinds
- What regulatory, resource, or environmental limits constrain growth?
- Where is competitive intensity creating pricing pressure?
- What substitution risks exist from adjacent industries or technologies?
- How does cyclicality affect the industry?

4. Technology Evolution
- What technologies are having material economic impact?
- How are cost curves expected to shift over the next 5-10 years?
- What role will automation, AI, and data play in reshaping margins?

5. Competitive Landscape Shifts
- Who are the emerging challengers and disruptors?
- What consolidation trends are underway?
- Which economic moats are strengthening, and which are eroding?

6. Scenarios (5-10 Year Horizon)
- Base case: What happens if current trends continue?
- Upside case: What could accelerate growth beyond expectations?
- Downside case: What shocks could derail the industry?
- Assign rough probability estimates and identify leading indicators for each scenario

7. Financial Outlook
- What are realistic expectations for revenue growth, margins, and return on capital?
- How capital-intensive is growth likely to be?
- What valuation frameworks are most appropriate for this industry?

8. Strategic Implications
- What capabilities and assets will define winners in the next decade?
- Where should capital flow, and where should it avoid?
- What structural risks must investors monitor?

OUTPUT REQUIREMENTS
- Use current data and cite sources
- Be specific about timeframes and magnitudes
- Distinguish between high-confidence projections and speculative scenarios
- Conclude with a clear summary of the investment implications

Prompt 3: Industry Engine (Operations & Economics)

ROLE
You are an industry economist and operations analyst specializing in [Industry Name] in [Country/Region].

OBJECTIVE
Create a technical analysis (~ 10,000 words) that explains exactly how this industry operates — how inputs become outputs, how money flows through the system, and what separates excellent operators from mediocre ones. Focus on the mechanics that drive profitability.

RESEARCH FOCUS

1. Value Chain Architecture
- Map every stage from raw inputs to end customer
- Identify the key actors at each stage (suppliers, manufacturers, distributors, retailers, platforms)
- Quantify where value is created and captured
- Explain how materials, information, and cash flow through the system

2. Revenue Models
- What are the typical pricing mechanisms? (per-unit, subscription, spread-based, fee-based)
- How do companies balance capacity utilization vs. demand management?
- What is the mix of fixed vs. variable revenue?
- How sensitive is pricing to input cost changes?

3. Cost Structure Deep-Dive
- Break down operating costs: raw materials, energy, labor, logistics, depreciation, maintenance, marketing, regulatory compliance
- What percentage does each cost category represent?
- Where are the economies of scale, scope, and density?
- What costs are fixed vs. variable, and where are the non-linear behaviors?

4. Working Capital Dynamics
- What are typical payment cycles? (receivables, payables, inventory days)
- What drives cash conversion efficiency?
- Are there seasonal patterns in cash flow?
- How do prepayments, float, or deferred revenue affect the business?

5. Asset Base & Capital Requirements
- What does the typical asset base look like? (plants, equipment, technology, licenses)
- How capital-intensive is this industry?
- What is the split between maintenance capex and growth capex?
- How does operating leverage affect profitability at different utilization levels?

6. Labor & Productivity
- What portion of costs is labor?
- What is the skill composition of the workforce?
- What is the automation potential?
- How do labor regulations and unionization affect cost flexibility?

7. Technology & Process
- What core technologies drive efficiency?
- How much do companies spend on IT and process improvement?
- What process innovations have materially changed margins in recent years?

8. Regulatory & Compliance Costs
- What mandatory compliance processes exist? (safety, environmental, quality, data)
- How do these affect throughput, cost, and ability to scale?
- Are there licensing or certification bottlenecks?

9. Risk & Resilience
- What are the key operational risks? (supply disruption, energy prices, logistics)
- Where are single points of failure?
- How do leading companies build redundancy?
- What macro variables most affect operations? (interest rates, currency, commodity prices)

10. Performance Benchmarks
- What are the core KPIs? (gross margin, EBITDA margin, ROCE, asset turnover, capacity utilization)
- What do median vs. top-quartile performers look like?
- Which operating metrics most strongly predict long-term value creation?

11. What Separates the Best Operators
- What practices do industry leaders consistently use?
- Quantify the margin or return advantage of best-in-class operations
- What can investors look for to identify operational excellence?

OUTPUT REQUIREMENTS
- Be specific and quantitative wherever possible
- Use industry-specific terminology and metrics
- Cite sources for benchmarks and data points
- Conclude with a checklist of operational factors investors should evaluate

After Running the Prompts

Once you have all three reports, export them as google docs from Gemini. These become your foundational sources, your AI analyst’s crash course on the industry.

But they’re just the beginning.

Now comes the layering.

Step 1: Import Your Foundation

Open NotebookLM and create a new notebook. Import your three Gemini Deep Research docs. You’ve used 3 of your 50 source slots(free plan), and you already have a comprehensive knowledge base covering the industry’s origin, trajectory, and operating mechanics.

Step 2: Add Company Annual Reports

Before using NotebookLM’s discovery features, manually add 5-7 annual reports from companies across the value chain. These give you ground-truth data that no AI-generated report can match, management commentary, segment breakdowns, risk disclosures, capex plans.

For a specialty chemicals analysis, you might add:

• 2 upstream players (raw material suppliers)

• 2-3 midstream manufacturers (the core industry)

• 2 downstream customers or distributors

Download these directly from company investor relations pages or screeners and upload them as PDFs. You’ve now used roughly 10 of your 50 slots.

Step 3: Discover Additional Sources (The Smart Way)

Here’s where NotebookLM’s native intelligence shines.

NotebookLM’s ‘Discover Sources’ feature understands Google search operators. This means you can be surgical about what it finds. Instead of a vague topic description, use structured prompts that target specific source types.

For consultancy and research reports:

[Industry Name] industry analysis filetype:pdf site:mckinsey.com OR site:deloitte.com OR site:ey.com OR site:bcg.com OR site:bain.com after:2024

[Industry Name] market outlook 2025 filetype:pdf site:kpmg.com OR site:pwc.com

For government and regulatory body reports:

[Industry Name] policy report filetype:pdf site:gov.in OR site:nic.in after:2023

For global industries:

[Industry Name] industry report filetype:pdf site:unido.org OR site:oecd.org OR site:worldbank.org

For industry association publications:

[Industry Name] association annual report 2024 filetype:pdf

[Industry Name] industry body white paper market size

For recent data and trends:

[Industry Name] market size growth 2025 after:2024-06-01

Review what NotebookLM returns. Uncheck generic news articles or low-quality sources. Select the substantive reports, the ones with actual data, frameworks, and analysis. Add them to your notebook.

Step 4: Fill Gaps with Deep Research

If Discover Sources doesn’t surface what you need, especially for niche industries or specialized regulatory bodies, use NotebookLM’s Deep Research feature.

Unlike Discover Sources (which returns 10 quick results), Deep Research spends 3-5 minutes browsing hundreds of websites and compiles a comprehensive report with 15-25 cited sources.

Use prompts like:

Find recent industry reports, regulatory filings, and policy documents for [Industry Name] in [Country/Region]. Focus on market size data, growth projections, and regulatory frameworks published after January 2024.

Identify official publications from [Specific Regulatory Body or Industry Association] related to [Industry Name] sector analysis, annual reviews, or market outlook reports.

Deep Research will return both a synthesised report and a list of sources (cited and uncited). Import the report and cherry-pick the highest-quality sources.

Step 5: Manual Sourcing for Stubborn Gaps

Sometimes, especially for niche industries, AI-powered discovery misses important sources. Government ministry reports, obscure industry association publications, or regional regulatory body documents often don’t surface automatically.

When this happens, go to Google directly and use these search patterns:

For Indian government and ministry reports:

site:ibef.org [Industry Name] report filetype:pdf
site:makeinindia.com [Industry Name]
site:pib.gov.in [Industry Name] policy
[Industry Ministry Name] annual report filetype:pdf

For industry associations (when you know the name):

site:[association-website] annual report OR market outlook filetype:pdf

For CRISIL/ICRA/FICCI commissioned research:

[Industry Name] CRISIL report filetype:pdf after:2023
[Industry Name] FICCI study filetype:pdf

For global equivalents:

site:trade.gov [Industry Name] market overview (US International Trade Administration)
site:ec.europa.eu [Industry Name] industry report (European Commission)

Once you find these sources, download the PDFs and upload them directly to your NotebookLM notebook.

Managing Your 50-Source Limit (on free plan)

By now, you might have:

• 3 foundational Gemini Deep Research reports

• 5-7 company annual reports

• 10-15 discovered/researched sources (consultancy reports, regulatory documents)

• 5-10 manually sourced niche publications

That’s 25-35 sources, leaving room for ongoing additions as you deepen your research.

Quality matters more than quantity. A notebook with 30 carefully selected sources will outperform one stuffed with 50 mediocre ones. Be ruthless about what you include.

Pro Tip: Add Primary Research Through Earnings Calls

Everything we’ve discussed so far, consultancy reports, government publications, annual reports, is secondary research. Valuable, but filtered.

There’s one source type that gets you closer to primary research: earnings call transcripts.

These are unscripted conversations between professional analysts and company management. The analysts ask pointed questions about industry headwinds, competitive dynamics, pricing pressure, supply chain risks. The management responds in real-time and their tone, confidence, and hesitation reveal things no polished annual report ever will.

When a specialty chemicals CEO discusses China+1 tailwinds or feedstock pricing volatility, they’re not just talking about their company. They’re giving you a window into the entire industry.

How to do this:

1. Identify 3-4 leadership companies across the value chain: one from upstream (raw materials/suppliers), one from the core industry (manufacturers), one from downstream (distributors or end-users). Don’t worry about finding “good management”, just pick the market leaders in each segment. Leaders see the industry most clearly because they shape it.

2. Download recent earnings call transcripts: For Indian companies, go to Screener.in and download con call transcripts directly from company pages. For US and global companies, use Finviz or the company’s investor relations website.

3. Summarize them into one industry-level report: Upload all transcripts to Gemini and use a simple prompt:

Summarize these earnings call transcripts into a single industry analysis report. Focus on: industry outlook, competitive dynamics, supply chain commentary, pricing trends, regulatory concerns, and management sentiment. Highlight where multiple managements agree or disagree.

4. Upload the synthesis to your notebook: Export Gemini’s output as a PDF and add it to NotebookLM. One source slot. High-value primary research synthesis.

This is as close as a retail investor gets to sitting in a room with industry insiders. Use it.

Building Your Notebook

You have the framework. You have the prompts. You have the source discovery strategy.

Now let’s put it all together.

This section is a step-by-step walkthrough of building an industry research notebook from scratch. I’ll use Indian Specialty Chemicals as the running example, but the process is identical for any industry, any geography.

Step 1: Create Your Notebook

Go to notebooklm.google.com and click “New Notebook.”

Name it clearly. I use a format like:

• Industry Research: Indian Specialty Chemicals

• Industry Research: European Automotive

• Industry Research: US Data Centers

The naming convention matters when you’re managing multiple notebooks. You’ll thank yourself later.

Step 2: Generate Your Foundation Reports

Open Gemini (gemini.google.com) in a separate tab. Select Deep Research mode.

Run the three prompts we covered earlier: Origin, Trajectory, and Engine, one at a time. For Indian Specialty Chemicals, my prompt inputs looked like:

• Industry Origin: [Industry Name] → Indian Specialty Chemicals, [Country/Region] → India

• Industry Trajectory: Same substitution

• Industry Engine: Same substitution

Each report takes 3-5 minutes. Let them run in the background.

Once complete, export each as a google doc. You now have three comprehensive reports, probably 8,000-10,000 words each, synthesised from hundreds of web sources.

Step 3: Import Foundation + Annual Reports

Upload your three Gemini docs to the notebook.(or simply add the doc link)

Then add 5-7 annual report from companies across the industry.

For Indian Specialty Chemicals, I selected:

• Diversified players: Deepak Nitrite (basic + specialty + phenolics), SRF (fluorochemicals + specialty chemicals)

• Core specialty manufacturers: Aarti Industries, Navin Fluorine, Vinati Organics

• Application-focused: PI Industries (agrochemical contract manufacturing)

The goal is coverage across different chemistries, end-markets, and business models, not a strict supply chain sequence.

You’ve now used about 10 source slots.

Step 4: Discover Additional Sources

Use NotebookLM’s Discover Sources feature to find consultancy and regulatory reports.(Alternatively use Google search)

Run targeted prompts like:

specialty chemicals India industry analysis filetype:pdf site:mckinsey.com OR site:deloitte.com OR site:ey.com after:2024

specialty chemicals India policy report filetype:pdf site:gov.in OR site:ibef.org

Indian chemical industry market outlook 2025 filetype:pdf

Review what surfaces. Select the substantive reports, skip news articles and generic overviews. Import them.

Step 5: Run Deep Research for Gaps

If Discover Sources doesn’t surface regulatory or association reports, use NotebookLM’s Deep Research feature:

Find official publications and reports from Indian Chemical Council, Chemexcil, Department of Chemicals and Petrochemicals, and FICCI related to specialty chemicals industry analysis, market size, and growth projections published after January 2024.

Import the synthesized report and cherry-pick quality sources.

Step 6: Add Earnings Call Synthesis (Optional but Recommended)

Download recent earnings call transcripts from Screener.in for 3-4 leading companies.

Upload them to Gemini with the prompt:

Summarize these earnings call transcripts into a single industry analysis report. Focus on: industry outlook, competitive dynamics, supply chain commentary, pricing trends, regulatory concerns, and management sentiment. Highlight where multiple managements agree or disagree.

Export as PDF. Import to your notebook.

Step 7: Let NotebookLM Process

After importing all sources, give NotebookLM a few minutes to process everything. You’ll see source summaries appear.

Once processing is complete, your notebook is ready.

What You’ve Built

At this point, you have a research desk that contains:

• Comprehensive historical, growth, and operational analysis of the industry

• Management perspectives from leading companies

• Consultancy frameworks and market sizing

• Regulatory and policy context

• Primary research synthesis from earnings calls

All citation-backed. All searchable. All in one place.

A professional analyst before AI would take 2-3 weeks to compile this. You did it in an afternoon.

Talking to Your Notebook

A desk full of reports is useless if you don’t know what to ask.

This is where most people go wrong with AI tools. They upload documents and ask vague questions like “summarize this” or “what should I know about this industry?” The responses are predictably generic.

NotebookLM is different. It only answers from your sources, with citations. But that constraint is only valuable if you ask questions sharp enough to extract real insight.

Here’s how to think about it.

The Three Levels of Questions

Level 1: Fact Extraction

These are straightforward queries where you need specific data points buried in your sources.

• What is the current market size of the Indian specialty chemicals industry?

• What are the major raw materials used in fluorochemical production?

• Which companies have announced capacity expansions in the last two years?

• What environmental regulations affect specialty chemical manufacturers in India?

NotebookLM handles these effortlessly. It finds the data, cites the source, and you move on.

Level 2: Synthesis & Comparison

These questions force NotebookLM to connect information across multiple sources, where the real value emerges.

• How do the gross margins of fluorochemical players compare to agrochemical-focused companies, and what explains the difference?

• What do management commentaries across companies say about China+1 tailwinds, are they consistent or contradictory?

• How has the regulatory environment evolved over the past five years, and which companies have benefited or suffered?

• Compare the capex strategies of SRF and Aarti Industries, what do their investment priorities reveal about where they see future growth?

These questions produce answers you won’t find in any single report. They emerge from the collision of multiple perspectives in your notebook.

Level 3: Implication & Judgment

These are the questions that turn research into investment insight.

• Based on the sources, what structural advantages do Indian specialty chemical companies have over Chinese competitors and how durable are they?

• What risks are mentioned across multiple annual reports but rarely discussed by analysts?

• If environmental regulations tighten further, which business models are most vulnerable?

• What would need to be true for this industry to sustain 10% growth for the next decade?

NotebookLM won’t give you opinions. But it will synthesise what your sources say about these questions and that synthesis, grounded in real documents, is far more valuable than an AI’s speculation.

Question Frameworks That Work

When you’re stuck, use these templates:

For understanding economics:

• What drives profitability in [segment]? What are the key cost components?

• How do companies in this industry generate returns on capital?

• What is the typical working capital cycle, and which companies manage it best?

For competitive dynamics:

• What barriers to entry exist, and how have new entrants overcome them?

• How do companies differentiate: is it cost, technology, relationships, or scale?

• What do management commentaries reveal about competitive intensity?

For identifying risks:

• What risks are disclosed in annual reports that aren’t widely discussed?

• How exposed is this industry to regulatory changes, commodity prices, or currency fluctuations?

• What single points of failure exist in the supply chain?

For spotting opportunities:

• Which segments are growing faster than the overall industry?

• Where are companies investing most aggressively, and why?

• What adjacencies or new applications are being mentioned?

A Practical Example

Let’s say you’re trying to understand whether the China+1 narrative is real or just hype.

Don’t ask: “Is China+1 benefiting Indian specialty chemicals?”

Instead, ask a sequence:

1. “Which companies mention China+1 or supply chain diversification in their annual reports or earnings calls? Quote the specific statements.”

2. “What evidence do management commentaries provide about actual order wins or customer shifts from China?”

3. “Are there any contradictions, companies that mention China+1 as an opportunity but haven’t shown revenue gains from it?”

4. “Based on the sources, what is required for an Indian company to actually capture business shifting from China?”

This sequence moves from data → evidence → contradictions → implications. By the end, you have a grounded, nuanced view, not a headline.

One Rule

Ask questions you actually care about.

If you’re researching an industry for investment purposes, the questions that matter are the ones that would change your decision. What would make you invest? What would make you avoid? What would make you pay a higher multiple?

Work backwards from those questions.

Pro Tip: Organize Your Sources for Precision Queries

Once you’ve added 30-40 sources, your notebook can feel overwhelming. Here’s a naming convention that transforms it into a structured research system.

Rename each source with a prefix that categorizes it:

Why this matters:

NotebookLM lets you select which sources to query. With organized naming, you can:

• Select only AR: sources to understand company-specific perspectives

• Select only Tier 1: sources to get consultancy-grade frameworks

• Select only Pillar 1: to deep-dive into historical context

• Mix Tier 1: + Tier 2: for a policy-meets-strategy view

You can extend this further based on your research needs: add prefixes like User: for customer pain point research, Competitor: for competitive analysis sources, or any category that helps you slice your notebook precisely.

The goal: never scroll through 40 sources hunting for the right one. Just select by prefix and query.

Your Ready-to-Use Notebook

I’ve shown you how to build an industry research notebook from scratch. But I also want you to experience what it feels like to use one.

So I’ve built an Indian Specialty Chemicals notebook using this exact framework and I’m sharing it with you.

Click to View My Notebook

What you’ll get:

• Foundational reports covering the industry’s origin, trajectory, and operating mechanics

• Annual reports from leading players across different chemistries and business models

• Consultancy and regulatory sources for policy context

• Earnings call synthesis for management perspectives

Use it to explore. Ask questions. See what it’s like to have your own industry research desk at work.

One request: This notebook is publicly shared with open access. If anything is removed, I can’t restore it. Explore freely, but please don’t modify sources so others can benefit too.

When you’re ready to go deeper, build your own.

Maintaining and Scaling

You’ve built your first industry research notebook. But industries evolve, companies report new numbers, regulations change. Here’s how to keep your notebook useful over time.

Keeping Your Notebook Current

Structural industry analysis, the origin, competitive dynamics, operating economics, stays relevant for years. But some sources need periodic refreshing.

Refresh annually:

• Company annual reports (add new ones when released)

• Consultancy reports (check for updated industry outlooks)

• Regulatory body publications (new policy documents, market sizing)

Refresh quarterly (if actively tracking the sector):

• Earnings call synthesis (run fresh summaries after each earnings season)

Don’t refresh:

• Your foundational Gemini reports (Origin, Trajectory, Engine), these capture structural understanding, not current events

A simple system: set a calendar reminder at the start of each financial year to update your active notebooks. One afternoon per notebook keeps everything current.

Scaling to Multiple Industries

Once you’ve built one notebook, you’ll want more. One principle matters most: prioritize depth over breadth.

A well-maintained notebook with 40 high-quality sources beats five half-built notebooks with 15 sources each. Build fewer, go deeper.

When to Build a New Notebook

Not every research question needs a full notebook. Use this as a guide:

Build a notebook when:

• You’re seriously evaluating investments in a sector

• You expect to track the industry for 2+ years

• Multiple companies in your portfolio or watchlist operate in this space

• The industry is complex enough that you can’t hold it all in your head

Don’t build a notebook when:

• You’re doing a quick one-time lookup

• The industry is too niche to have 20+ quality sources

• You’re researching a single company, not an industry

For single-company research, a simpler approach works, upload that company’s annual reports and a few competitor reports into a lightweight notebook. No need for the full framework.

The Compounding Effect

Here’s what happens over time:

Year one, you build 2-3 industry notebooks. You understand those sectors better than most professional analysts.

Year two, you add 2-3 more and update the originals. You start seeing cross-industry patterns, how regulatory changes in one sector mirror another, how capital cycles rhyme across industries.

Year three and beyond, you have a personal research library that no subscription service can replicate. It’s tailored to your interests, updated on your schedule, and built on your analytical framework.

That’s the real payoff. Not one notebook, a system that compounds.

When I started, nobody handed me a system like this. I had to figure it out the hard way.

You don’t have to.

That’s why I built Alpha with AI.

What’s Coming Next Week

→ Insider Trading Dashboard: Map buys, sells, conviction signals automatically

🤝 Help Us Grow This Circle

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

Share Alpha with AI

Bonus: SuperAnalyst Command Centre

Research doesn’t fail because of bad analysis. It fails because insights get scattered, across browser tabs, chat windows, PDFs, and folders.

That’s why I built the SuperAnalyst Command Centre.

A Notion-based AI research system where:

• Perplexity gathers intelligence

• NotebookLM analyzes documents

• Notion AI connects everything

Every insight stays linked. Ask it a question months later, it remembers.

The Basic Version is free. The Pro Version unlocks the full workflow.

Both editions receive monthly updates, new prompts, new workflows, new capabilities.

Research evolves. Your system should too.

SuperAnalyst Command Centre

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

Because the future of analysis isn’t about who knows Excel best.

It’s about who builds thinking systems that scale.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Guide & Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Last month, an equity research analyst reached out with an unusual request.

Unusual because of who he was. Two decades of building financial models. Covered sectors across the market. Trained junior analysts. The kind of analyst who can spot red flags in a balance sheet before the auditors do.

Yet here he was, asking about AI.

Not skeptically. More like someone who’d been watching from the sidelines and finally decided to step onto the field.

“I’ve built thousands of models,” he said. “I know how to do this. But I don’t want to spend six hours on what should take one. I don’t want to chase formula errors at midnight anymore.”

Then he said something that stuck with me.

“Building the model isn’t the hard part. Anyone can learn that in thirty days. The hard part is knowing what questions to ask once it’s built. That’s where twenty years shows up. That’s what I should be spending my time on.”

He was right.

Extracting numbers, linking formulas, debugging why the balance sheet doesn’t balance, none of that is analysis. It’s administration. The real work starts after the model is built.

So I built him something. A system that creates 13-sheet integrated financial models with three-statement flows and DCF valuation. Tested it. Fixed the gaps. Refined it until it worked the way a model built by a serious analyst would work.

And now I’m giving it away.

Not the exact version customized for him. But the core framework, packaged as a Claude Skill you can deploy in under few minutes.

This newsletter documents everything: how the skill works, how to set it up, and what changes when you can build models in an hour instead of six.

Let’s begin.

What This Skill Actually Does

Before we get into setup, let me show you what you’re getting.

The Integrated Financial Modeling Skill creates a complete 13-sheet Excel model with:

Core Financial Statements (Sheets 1-5)

• Introduction: Company overview, key metrics, current valuation

• Consolidated P&L: Profit & Loss with projections

• Consolidated Balance Sheet: Always balances

• Consolidated Cash Flow Statement: Always reconciles

• Reconciliation: Cash validation check

Analysis Sheets (Sheets 6-8)

• Ratio Analysis: 30+ financial ratios across all periods

• Common Size P&L: Vertical analysis (% of revenue)

• Common Size BS: Vertical analysis (% of assets)

Supporting Schedules (Sheets 9-11)

• Revenue Model: Bottom-up revenue build from drivers

• Quarterly Data: Latest quarters for tracking

• Capex Model: Fixed assets and depreciation schedule

Valuation (Sheets 12-13)

• DCF Valuation: Three methods: Gordon Growth, FCFE, FCFF with sensitivity tables

• Scenarios: Bear/Base/Bull cases

Everything is formula-driven. Historical years pull from annual reports. Projection years are 100% formulas linked to assumptions. Change one input, and the entire model updates, P&L flows to Balance Sheet, Balance Sheet changes drive Cash Flow, Cash Flow reconciles back.

No hardcoding. No broken links. No midnight debugging.

The DCF sheet alone runs three independent valuations and averages them for a final target price. Two sensitivity tables show you how the valuation moves with different discount rates and growth assumptions.

This is the structure institutional analysts use. Now it’s yours.

What You Need Before Starting

This skill runs on Claude, Anthropic’s AI. You’ll need a few things set up before you can use it.

1. Claude Pro Plan

The Skills feature requires Claude Pro. It costs $20/month (roughly ₹1,800).

Go to claude.ai, sign up, and upgrade to Pro from Settings. Without Pro, you won’t have access to Skills or Projects, both of which this system requires.

2. Enable Skills

Once you’re on Pro:

• Go to Settings → Capabilities → Skills

• Turn on the toggle for Skill Creator (Beta)

This allows Claude to read custom skill files you upload.

3. Download the Skill Package

I’m giving away the complete skill as a zip file. It contains:

• SKILL.md: The main instruction file Claude reads

• references/: Detailed methodology guides, DCF specifications, prompt templates

• examples/: A working template model for reference

Skill Download link

• Download that .zip file to your computer.

• You’ll upload this file in the next step.

• Go back to Settings → Capabilities → Skills

• Click Upload Skill

• Drag and drop the downloaded .zip file into the upload window.

• Wait for confirmation, your Skill will now appear under My Skills.

Now you’re ready to generate full financial models, instantly.

One more hack.

Want to use your own in-house template instead of the one provided?

Start a new chat. Upload the skill zip file along with your own Excel model template. Then say:

“I want to follow the structure of this template instead of the current skill template. Update the skill accordingly.”

Claude will decode the skill, make the necessary changes to match your template’s structure and formatting, and give you a new zip file. Upload that to your project, and you’re set with a customized skill built around your own standards.

Demo to upload this skill:

4. Financial Data from Perplexity Finance

Go to perplexity.ai/finance and search for your company. Download the Excel file, it includes balance sheet, cash flow statement, P&L, and key statistics across multiple years.

One thing to note for Indian companies: the downloaded Excel sometimes shows the currency unit as “USD” or “Billion USD” at the top, even though all figures are actually in Indian Rupees. Just edit that header to show the correct unit (₹ Crores or ₹ Lakhs) before uploading to Claude.

That’s it. Pro plan, skills enabled, skill package downloaded, financial data ready.

Now let’s set it up.

Setting Up Your Claude Project

The skill package includes a detailed setup guide. Follow it step by step. Once you upload the skill, click on the skill and find the guide in the references section.

Step 1: Create New Project

Go to claude.ai. Click “Projects” in the left sidebar, then “New Project.”

• Name: Integrated Financial Modeling

• Description: Build 3-statement financial models with DCF valuation for listed companies

Step 2: Upload All Files

Unzip the skill package you downloaded. Upload everything to your project’s Knowledge section:

• SKILL.md

• All files from the references/ folder

• The template from examples/ folder

Step 3: Add Custom Instructions

Open project_setup_guide.md from the references folder. Find the Custom Instructions section (Step 3 in that guide).

Copy the entire instruction block and paste it into your project’s Custom Instructions.

This tells Claude exactly how to build models, what standards to follow, and what quality checks to run.

Step 4: Start Building

Open a new chat inside your project. Upload the Perplexity Finance Excel for your company.

Say:

“Build an integrated financial model for [Company Name] using the uploaded data.”

Claude reads the skill files, extracts your data, and builds the complete 13-sheet model.

What Happens When You Run It

Here’s the important part. Claude will build your model, but it needs your inputs. Otherwise, it makes assumptions on its own and you want control over those assumptions.

Open quick_prompt_templates.md from the references folder. At the top, you’ll find the Master Prompt. This is what you use.

It looks like this:

Fill in the blanks. Current market price, your growth assumptions, margin expectations, working capital days, beta, risk-free rate, all of it. The more you specify, the more the model reflects your view. Leave things blank, and Claude will assume defaults based on historical trends.

Once your inputs are ready, paste the prompt into your project chat along with the Perplexity Finance Excel file.

Claude reads the skill files, extracts the financial data, and builds the model using your assumptions. It populates historical years first, verifies the balance sheet balances, confirms cash flow reconciles, then moves to projections. Finally, it builds the DCF with all three valuation methods, runs sensitivity analysis, and delivers the Excel file.

What used to take six hours is now completely automated.

Edit, Analyze, and Reuse

Once downloaded, the model is completely editable.

You can tweak assumptions, stress-test cases, and rerun new versions, all in minutes, not hours.

But here’s the thing, the first output isn’t always perfect. Formulas might not connect across sheets. Rows and columns might mismatch. Something might not tally.

When that happens, re-upload the Excel file or just ask a follow-up: “The balance sheet isn’t balancing in FY26E. Can you check and fix it?” or “Depreciation in P&L doesn’t match the Capex Model. Please re-link.”

Keep iterating. Ask Claude to re-verify until you get a clean model. You can do this manually too, but Claude speeds up the debugging significantly.

The Skill Package: What’s Inside

Here’s what you get when you download the skill:

integrated-financial-modeling/
├── SKILL.md
├── README.md
├── LICENSE.txt
├── references/
│   ├── financial_modeling_methodology.md
│   ├── enhanced_dcf_specification.md
│   ├── quick_prompt_templates.md
│   └── project_setup_guide.md
└── examples/
    └── JK_Paper_Template.xlsx

SKILL.md: The main file Claude reads. Contains the 13-sheet structure, core principles, DCF methods, quality checks.

financial_modeling_methodology.md: The complete 100+ page guide. Every sheet explained. Every formula documented. Projection methodologies. Troubleshooting steps.

enhanced_dcf_specification.md: Detailed DCF structure with all three valuation methods, sensitivity tables, and complete formula references.

quick_prompt_templates.md: Ready-to-use prompts. Master prompt for full models. Stage-by-stage prompts. Troubleshooting prompts.

project_setup_guide.md: Step-by-step setup instructions. Custom instructions to copy-paste. Example conversations.

JK_Paper_Template.xlsx: A working reference model.

Closing

That analyst I mentioned at the start? He’s been using this for two weeks now.

Last I heard, he’d built models for 3 companies. Said he’s spending more time reading management commentary and thinking about business quality than fixing Excel errors.

That was the whole point.

Financial modeling hasn’t changed in thirty years. The same manual extraction. The same formula linking. The same midnight debugging. AI should have fixed this by now.

Now it can.

The skill is free. The setup takes under an hour. The models that come out are institutional-grade, 13 sheets, fully integrated, three DCF methods, sensitivity analysis included.

What you do with the extra time is up to you.

Download the skill. Build your first model. And if you find ways to make it better, I’d love to hear about it.

What’s Coming Next Week

A complete framework to research any industry, in any geography, from scratch using AI.

🤝 Help Us Grow This Circle

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

Share Alpha with AI

Bonus: SuperAnalyst Command Centre

Research doesn’t fail because of bad analysis. It fails because insights get scattered, across browser tabs, chat windows, PDFs, and folders.

That’s why I built the SuperAnalyst Command Centre.

A Notion-based AI research system where:

• Perplexity gathers intelligence

• NotebookLM analyzes documents

• Notion AI connects everything

Every insight stays linked. Ask it a question months later, it remembers.

The Basic Version is free. The Pro Version unlocks the full workflow.

Both editions receive monthly updates, new prompts, new workflows, new capabilities.

Research evolves. Your system should too.

SuperAnalyst Command Centre

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

Because the future of analysis isn’t about who knows Excel best.

It’s about who builds thinking systems that scale.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Guide & Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

August 5, 2024.

Global markets were bleeding.

• Japan: -13%

• Korea: -10%

• Taiwan: -10%

• Nasdaq Futures: -5%

I sent this note to my clients that day:

I understood exactly what was happening.

Japan had raised rates by 0.25%. The yen carry trade, a $2 trillion arbitrage that had quietly funded global risk appetite for two decades, was unwinding. Money was rushing back to Japan.

My read on the trigger? Spot on.

My call on timing? Completely wrong.

What actually followed:

• Indian markets severely underperformed

• Correction dragged on till March 2025

• Six more months of consolidation

• Over 12 months of pain

I told clients “next few days/weeks.”

It took over a year.

I understood the WHAT.

I completely misjudged the HOW LONG.

That failure has stayed with me for 14 months.

What did I miss?

Right Trigger. Wrong Duration.

Here’s what I got right:

• The trigger (BOJ rate hike)

• The mechanism (yen carry trade unwinding)

• The strategy (avoid triple digit P/E stocks)

Here’s what I got wrong:

• Duration

One word. That’s all it took to turn a good analysis into a bad call.

Understanding what is happening is easy now. X(Twitter), Bloomberg, NSE data, it’s all there.

But knowing how long the pain lasts? That’s where everyone struggles.

Hedge funds have systems for this. Real-time flows. Scenario models. Duration frameworks.

Retail investors get the news after the first move is done.

We know the “what.” We guess the “how long.”

That guess cost my clients 12 months of opportunity cost.

This is the gap I wanted to close.

Closing The Gap

So I built an AI workflow that does what I couldn’t do manually in August 2024.

It doesn’t just identify triggers. It models scenarios and maps how global events transmit to local markets.

What it does:

• Pulls live BOJ policy data, yield curves, and FII flows

• Runs institutional-grade scenario analysis (dovish, base, hawkish)

• Maps which sectors break first and where money rotates

• Outputs a visual dashboard anyone can actually read

Time to run: 13 minutes.

Cost: Zero.

The workflow has two parts:

1. Data gathering (Perplexity): pulls real-time market data with sources

2. Analysis engine (Claude): runs scenario modeling and generates the report

You can run it for any macro trigger. Any market. Any sector focus.

Let me show you how.

Before You Run The Prompt

This workflow has two steps:

Step 1: Gather real-time data (Perplexity)

Step 2: Run the analysis (Claude, Grok, or any reasoning model)

For Step 1, you don’t need to download anything. Perplexity pulls live data from BOJ, RBI, NSE, and other public sources.

Just run the data gathering prompt first. Copy the output. Paste it into the analysis prompt.

That’s it.

If you want more accuracy, you can optionally add:

• Latest FII/FPI flow data from NSDL

• Current Japan yield data from BOJ website

• Recent RBI policy statements

But the prompt works without these. Perplexity fills the gaps.

Tool Demo:

THE PROMPTS

Step 1: Data Gathering (Run in Perplexity)

Gather current market data for yen carry trade analysis. Cite sources for every data point.

DATE:[Enter date]
MY MARKET: [Your country - e.g., India, Nigeria, Germany, US]
MY CURRENCY: [Your currency - e.g., INR, NGN, EUR, USD]
MY CENTRAL BANK: [Your central bank - e.g., RBI, CBN, ECB, Fed]

JAPAN (Source of carry trade):
- BOJ Policy Rate
- Japan 10Y & 30Y Yields
- USD/JPY spot rate
- BOJ next meeting date
- Market-implied probability of rate hike
- Recent BOJ commentary (last 2 weeks)

US (Global benchmark):
- US 10Y Treasury Yield
- Fed Funds Rate
- Fed next meeting date

MY LOCAL MARKET:
- Local 10Y Government Bond Yield
- Central Bank Policy Rate
- USD/[My Currency] spot rate
- Foreign investor flows (current + previous month)
- Central bank next meeting date

CONTEXT:
- Japan’s US Treasury holdings (latest)
- Estimated yen carry trade size
- USD/JPY 12-month range
- US-Japan yield spread (current vs 1 year ago)
- Any carry trade unwind news (last 30 days)

Format as clean data table with sources.

Step 2: Analysis Engine (Claude / Grok)

# ════════════════════════════════════════════════════════════════════════
# YEN CARRY TRADE UNWIND ANALYSIS PROMPT
# ════════════════════════════════════════════════════════════════════════
# 
# PURPOSE: Generate institutional-grade research analyzing the Japan yen carry trade unwind and its implications for global and local markets.
#
# HOW TO USE: Fill in the INPUTS section below, then run the entire prompt.
# ════════════════════════════════════════════════════════════════════════

# ════════════════════════════════════════════════════════════════════════
# INPUTS (Fill in once - these values are used throughout the analysis)
# ════════════════════════════════════════════════════════════════════════

ANALYSIS_DATE = “”
# Example: “December 2025”, “Q1 2026”, “January 15, 2025”

OUTPUT_LENGTH = “Analyst Note”
# Options: “Full Report” (~5,000 words) | “Analyst Note” (~2,000 words)
# Default: Analyst Note

PRIMARY_MARKET = “”
# Examples: “India”, “US”, “Germany”, “Singapore”, “UK”, “Nigeria”, “Brazil”
# This determines which market receives detailed local analysis and recommendations

LOCAL_CURRENCY = “”
# Examples: “INR”, “USD”, “EUR”, “GBP”, “SGD”, “NGN”, “BRL”

LOCAL_CENTRAL_BANK = “”
# Examples: “RBI”, “Federal Reserve”, “ECB”, “BOE”, “MAS”, “CBN”, “BCB”

LOCAL_STOCK_EXCHANGE = “”
# Examples: “NSE/BSE”, “NYSE/NASDAQ”, “LSE”, “SGX”, “Xetra”, “NGX”, “B3”

SECTOR_FOCUS = “”
# Optional - leave blank for broad market analysis
# Examples: “Banking”, “Pharma”, “IT Services”, “Real Estate”, “Auto”
# If filled, you’ll get a dedicated deep-dive on this sector in your primary market

# ────────────────────────────────────────────────────────────────────────
# MARKET DATA (Enter current figures for accuracy - leave blank if unavailable)
# ────────────────────────────────────────────────────────────────────────

# Japan Data (Source of the carry trade)
BOJ_POLICY_RATE = “”                    # e.g., “0.50%”
JAPAN_10Y_YIELD = “”                    # e.g., “1.90%”
JAPAN_30Y_YIELD = “”                    # e.g., “3.43%”
USD_JPY_RATE = “”                       # e.g., “154.50”

# US Data (Global benchmark)
US_10Y_YIELD = “”                       # e.g., “4.25%”
FED_FUNDS_RATE = “”                     # e.g., “4.50%”

# Your Local Market Data
LOCAL_10Y_YIELD = “”                    # e.g., “6.85%” for India, “2.30%” for Germany
LOCAL_POLICY_RATE = “”                  # e.g., “6.50%” RBI repo rate
USD_LOCAL_CURRENCY_RATE = “”            # e.g., “84.50” for USD/INR
FOREIGN_INVESTOR_FLOWS = “”             # e.g., “FIIs sold $2.1B in November”

# ════════════════════════════════════════════════════════════════════════
# END OF INPUTS - Do not modify below this line
# ════════════════════════════════════════════════════════════════════════


# ROLE

You are a **Senior Economist & Cross-Asset Strategist** at a leading global brokerage with expertise in:
- Central bank policy transmission and macroeconomic analysis
- Cross-border capital flows and currency market dynamics
- Sector rotation and portfolio positioning across global markets
- Translating complex macro themes into actionable investment insights
- Behavioral finance and market cycle duration analysis

Your research is valued because you:
- Combine rigorous economic analysis with practical market implications
- Write with clarity and conviction, making complex dynamics accessible
- Provide specific, actionable recommendations rather than generic commentary
- Understand how global macro events transmit to local markets differently
- Analyze not just WHAT happens but HOW LONG the impact typically lasts

---

# TASK

Produce a **comprehensive investment research note** analyzing the **Japan yen carry trade unwind** as of **{ANALYSIS_DATE}**.

**Output Length:** 
- If {OUTPUT_LENGTH} = “Full Report”: ~5,500 words with all sections expanded
- If {OUTPUT_LENGTH} = “Analyst Note”: ~2,500 words, concise and action-focused

**Geographic Focus:**
- Primary analysis tailored to **{PRIMARY_MARKET}** investors
- Include global context but emphasize transmission to {LOCAL_CURRENCY} assets
- Sector recommendations should reference companies listed on {LOCAL_STOCK_EXCHANGE}

Your analysis will cover:
1. BOJ policy scenarios and what’s priced vs. what would surprise
2. Transmission mechanism to global rates AND specifically to {PRIMARY_MARKET}
3. Sector and asset class exposure mapping (which {PRIMARY_MARKET} sectors are vulnerable)
4. Tactical rotation playbook with specific {PRIMARY_MARKET} positioning recommendations
5. Scenario outcomes with positioning guidance
6. Duration modeling and behavioral lag analysis

---

# CONTEXT

## Carry Trade Mechanics (for reader reference)

The yen carry trade works as follows: Borrow yen at near-zero rates → Convert to higher-yielding currency (USD, EUR, {LOCAL_CURRENCY}) → Invest in higher-yielding assets (government bonds, equities, credit) → Pocket the spread.

**Why it matters now:** When Japanese rates rise or the yen strengthens, leveraged positions face margin pressure. Forced liquidation cascades through global markets because:
- Japanese institutions are the largest foreign holders of US Treasuries (~$1.1 trillion)
- Carry trade capital has flowed into EM assets, including {PRIMARY_MARKET} equities
- Unwinding creates correlated selling across asset classes

**Historical Reference:** In August 2024, the BOJ hinted at tightening. The yen spiked 10%+ in days. The Nikkei fell 13% in a single session (worst since 1987). S&P 500 fell 3%. Momentum and high-beta stocks globally were crushed. This serves as the template for how quickly carry unwinds can cascade.

**Critical Duration Lesson:** While the August 2024 trigger resolved within weeks, the market impact extended far longer. Indian markets, for example, underperformed for 12+ months following the initial shock. Fundamental triggers often resolve faster than behavioral reactions—institutional repositioning, retail capitulation, and sentiment normalization create extended pain cycles.

## Current Data Points

Use the following data provided by the user. If any field is blank, use web search to find the current figure and note the source.

**Japan:**
- BOJ Policy Rate: {BOJ_POLICY_RATE}
- Japan 10Y Yield: {JAPAN_10Y_YIELD}
- Japan 30Y Yield: {JAPAN_30Y_YIELD}
- USD/JPY: {USD_JPY_RATE}

**US (Global Benchmark):**
- US 10Y Yield: {US_10Y_YIELD}
- Fed Funds Rate: {FED_FUNDS_RATE}

**{PRIMARY_MARKET}:**
- {LOCAL_CURRENCY} 10Y Government Bond Yield: {LOCAL_10Y_YIELD}
- {LOCAL_CENTRAL_BANK} Policy Rate: {LOCAL_POLICY_RATE}
- USD/{LOCAL_CURRENCY}: {USD_LOCAL_CURRENCY_RATE}
- Recent Foreign Investor Flows: {FOREIGN_INVESTOR_FLOWS}

---

# OUTPUT STRUCTURE

## For “Analyst Note” (~2,500 words)

### Executive Summary (200-250 words)
A standalone summary covering:
- Core thesis in 2-3 sentences
- Key risk scenario and probability
- Most important {PRIMARY_MARKET} sector exposures
- Highest conviction rotation trade
- Expected duration range for market impact
- Primary uncertainty to monitor

### Current Market Snapshot (150-200 words)
**Required Table: Market Snapshot**
| Metric | Current | Historical Context |
|--------|---------|-------------------|
| BOJ Policy Rate | X% | vs. Y% one year ago |
| Japan 10Y Yield | X% | Highest since [year] |
| USD/JPY | XXX | vs. YYY range |
| {LOCAL_CURRENCY} 10Y Yield | X% | |
| USD/{LOCAL_CURRENCY} | XXX | |

Follow with 1-2 paragraphs noting:
- Which figures are historically unusual
- What the market is currently pricing for BOJ

### Section 1: BOJ Policy Scenarios (300-400 words)

**Required Table: BOJ Scenario Matrix**
| Scenario | Probability | Policy Path | USD/JPY Range | Surprise Factor |
|----------|-------------|-------------|---------------|-----------------|
| Dovish Hold | XX% | [description] | XXX-XXX | [what would surprise] |
| Base Case | XX% | [description] | XXX-XXX | [what’s priced] |
| Hawkish Acceleration | XX% | [description] | XXX-XXX | [what would surprise] |

Cover:
- What the BOJ is likely to do and why
- What’s priced vs. what would catch markets off-guard
- Where the asymmetric risk lies

**KEY TAKEAWAY:** 2-3 sentences on the highest-probability scenario and key risk.

### Section 2: Transmission to {PRIMARY_MARKET} (350-450 words)

Explain the transmission chain:
1. BOJ tightens → Yen strengthens
2. Japanese institutions repatriate capital → Sell foreign bonds
3. Global yields rise → Risk assets reprice
4. **{PRIMARY_MARKET} impact:** How this specifically affects {LOCAL_CURRENCY} and local assets

**{PRIMARY_MARKET}-Specific Analysis:**
- How does {LOCAL_CENTRAL_BANK} typically respond to global rate shocks?
- What is {PRIMARY_MARKET}’s exposure to foreign investor flows?
- Historical precedent: How did {PRIMARY_MARKET} perform during August 2024 mini-unwind?

**Required Table: Transmission Impact**
| Channel | Global Impact | {PRIMARY_MARKET} Impact |
|---------|--------------|------------------------|
| Bond yields | +XX bps on 10Y | +XX bps on {LOCAL_CURRENCY} 10Y |
| Currency | Yen +X% | {LOCAL_CURRENCY} [appreciation/depreciation] |
| Equity flows | Risk-off globally | FII outflows of $X estimated |

**KEY TAKEAWAY:** 2-3 sentences on primary transmission channel to {PRIMARY_MARKET}.

### Section 3: Sector Exposure Map (400-500 words)

**1st Order Effects (Direct Carry Destinations):**
Asset classes directly funded by yen borrowing - EM bonds, high-yield credit, levered equity strategies.

**2nd Order Effects (Rate-Sensitive Sectors in {PRIMARY_MARKET}):**

Analyze 3-4 vulnerable sectors in {PRIMARY_MARKET}. For each:
- Why it’s vulnerable
- 2-3 specific companies with tickers ({LOCAL_STOCK_EXCHANGE} listed)
- Key risk metric to watch

**Required Table: {PRIMARY_MARKET} Sector Vulnerability**
| Sector | Vulnerability Type | Key Risk Metric | Example Companies |
|--------|-------------------|-----------------|-------------------|
| [Sector 1] | [Rate sensitivity / FII exposure / Leverage] | [Metric] | [Tickers] |
| [Sector 2] | | | |
| [Sector 3] | | | |

**3rd Order Effects (Correlation Spike):**
What sells indiscriminately during deleveraging - momentum stocks, high-beta names, crowded trades.

**IF {SECTOR_FOCUS} is specified:**
Add dedicated subsection: **Deep Dive: {SECTOR_FOCUS} in {PRIMARY_MARKET}**
- 2-3 paragraphs analyzing this specific sector
- 3-4 vulnerable companies with brief rationale
- 2-3 relatively insulated companies

**KEY TAKEAWAY:** 2-3 sentences on highest-risk {PRIMARY_MARKET} sector.

### Section 4: Rotation Playbook (350-450 words)

**What to Favor in {PRIMARY_MARKET}:**
- Characteristics: Low leverage, domestic revenue, pricing power, strong balance sheets
- 2-3 sectors to favor with brief rationale
- 4-5 specific {LOCAL_STOCK_EXCHANGE} tickers with one-line rationale each

**What to Avoid in {PRIMARY_MARKET}:**
- Characteristics: High FII ownership, rate-sensitive, leveraged balance sheets
- 2-3 sectors to avoid with brief rationale
- 4-5 specific {LOCAL_STOCK_EXCHANGE} tickers with one-line rationale each

**Required Table: Rotation Summary**
| | FAVOR | AVOID |
|--|-------|-------|
| **Characteristics** | [list] | [list] |
| **Sectors** | [list] | [list] |
| **Top Picks** | [tickers] | [tickers to reduce] |

**KEY TAKEAWAY:** 2-3 sentences on highest-conviction trade.

### Section 5: Scenarios & Positioning (200-250 words)

**Required Table: Scenario Outcomes for {PRIMARY_MARKET}**
| Scenario | USD/JPY | {LOCAL_CURRENCY} 10Y | {PRIMARY_MARKET} Equity Index | Positioning |
|----------|---------|---------------------|------------------------------|-------------|
| Bear Case | XXX | X.XX% | -X% to -X% | [action] |
| Base Case | XXX | X.XX% | -X% to +X% | [action] |
| Bull Case | XXX | X.XX% | +X% to +X% | [action] |

**Key Uncertainties:**
- [Uncertainty 1]: Brief description
- [Uncertainty 2]: Brief description

**KEY TAKEAWAY:** 2-3 sentences on how to position given uncertainty.

### Section 6: Duration & Behavioral Analysis (300-350 words)

**Why Duration Matters:**
Identifying the trigger is only half the analysis. The August 2024 carry unwind demonstrated that fundamental triggers can resolve in weeks while market impact extends for months. Understanding behavioral lag is critical for timing.

**Historical Duration Patterns:**

**Required Table: Historical Carry Unwind Duration**
| Event | Trigger Resolution | Full Market Recovery | Key Extension Factor |
|-------|-------------------|---------------------|---------------------|
| 1998 LTCM/Asia Crisis | X weeks | X months | [factor] |
| 2008 GFC | X weeks | X months | [factor] |
| 2015 China Deval | X weeks | X months | [factor] |
| Aug 2024 BOJ Hike | ~2 weeks | 12+ months | Behavioral lag, FII persistence |

**Behavioral Lag Factors:**
Pain cycles extend beyond fundamentals due to:

→ **Institutional Reaction Lag**
- Large funds reposition over weeks/months, not days
- Forced liquidations trigger secondary selling waves
- Metric to watch: FII flow persistence (are they still selling weeks later?)

→ **Retail Reaction Lag**
- Retail investors often buy early dips, capitulate later
- SIP flows and mutual fund data indicate retail positioning
- Metric to watch: Retail mutual fund flow direction

→ **Sentiment Capitulation Markers**
- VIX/{PRIMARY_MARKET} volatility index levels
- Put-call ratios
- Analyst downgrades clustering

**Required Table: Duration Scenarios**
| Scenario | Trigger Resolution | Behavioral Lag | Total Duration Estimate |
|----------|-------------------|----------------|------------------------|
| Fast (V-shaped) | 2-3 weeks | +2-4 weeks | 1-2 months |
| Base (U-shaped) | 2-3 weeks | +2-4 months | 3-6 months |
| Extended (L-shaped) | 2-3 weeks | +6-12 months | 9-15 months |

**Signals That Extend Duration:**
- FII outflows persisting beyond 4 weeks
- Retail still buying dips (capitulation not complete)
- VIX remaining elevated above [threshold]
- {LOCAL_CENTRAL_BANK} forced to respond to currency pressure

**Signals That Shorten Duration:**
- FII flows stabilizing or reversing
- Retail capitulation complete (fund outflows spike then stop)
- Volatility normalizing
- BOJ signaling pause in tightening

**KEY TAKEAWAY:** Current signals suggest [X-shaped] recovery with estimated duration of [X months]. Key signal to watch: [specific metric].

---

## For “Full Report” (~5,500 words)

Expand each section as follows:
- Executive Summary: 300-400 words
- Current Market Snapshot: 250-350 words
- Section 1 (BOJ Policy): 750-1,000 words with deeper scenario analysis
- Section 2 (Transmission): 750-1,000 words with detailed mechanism explanation
- Section 3 (Sector Exposure): 1,200-1,500 words with more companies and granular analysis
- Section 4 (Rotation Playbook): 800-1,000 words with fuller rationales
- Section 5 (Scenarios): 500-700 words with more detailed scenario descriptions
- Section 6 (Duration & Behavioral): 600-800 words with deeper historical analysis

Add these additional elements for Full Report:
- Historical comparison section (past carry unwinds in detail)
- Detailed quantification of selling pressure scenarios
- Timeline of key dates to watch
- Risk monitoring checklist
- Behavioral capitulation framework with specific thresholds

---

# WRITING STYLE

**Tone:** Authoritative but accessible. Write like a senior strategist briefing portfolio managers who are smart but may not be macro specialists.

**Structure:** 
- Default to prose paragraphs, not bullets
- Use bullets only for discrete lists (tickers, characteristics)
- Every table must be introduced with context and followed by interpretation
- Each section needs a clear “so what” - never leave the reader wondering why they’re reading something

**Technical Terms:** Define macro jargon when first used. Example: “duration—the sensitivity of bond prices to interest rate changes”

**Specificity:** 
- Name specific companies with tickers, not just “banking stocks”
- Quantify where possible: “+30-50 bps” not “yields may rise”
- Give probability estimates: “60% base case” not “likely”
- Provide duration ranges: “3-6 months” not “several months”

**KEY TAKEAWAY Boxes:** Every section ends with a clearly labeled 2-3 sentence takeaway that a skimming reader could extract.

---

# REQUIRED TABLES CHECKLIST

Ensure all of these tables appear in the output:

1. ☐ Current Market Snapshot Table
2. ☐ BOJ Scenario Matrix Table  
3. ☐ Transmission Impact Table (with {PRIMARY_MARKET} column)
4. ☐ {PRIMARY_MARKET} Sector Vulnerability Table
5. ☐ Rotation Summary Table (FAVOR vs. AVOID)
6. ☐ Scenario Outcomes Table (with {PRIMARY_MARKET} metrics)
7. ☐ Historical Carry Unwind Duration Table
8. ☐ Duration Scenarios Table (V/U/L-shaped)

---

# WARNINGS

- Do NOT present scenarios as investment advice or price targets. Frame as probabilistic analysis for educational purposes.
- Do NOT fabricate data. If a figure is unavailable, state “Data unavailable—recommend verification” and use reasonable estimates clearly labeled as such.
- Do NOT use generic statements like “growth stocks may underperform.” Be specific: name industries, name companies, quantify impact ranges.
- Do NOT assume all readers are from {PRIMARY_MARKET}. Maintain global context while emphasizing local implications.
- Do NOT rely on bullets as a crutch. Default to prose with clear topic sentences.
- Do NOT present tables without context and interpretation.
- Do NOT conflate trigger resolution with full market recovery. Always separate fundamental resolution from behavioral normalization.
- If uncertainty is high, present a range of outcomes rather than false precision.

---

# EXECUTION STEPS

1. Check all INPUT fields - use web search to fill any blank data fields
2. Confirm OUTPUT_LENGTH and adjust section depths accordingly
3. Draft all sections in order, ensuring each has required table and KEY TAKEAWAY
4. Pay special attention to Section 6 (Duration) - this differentiates the analysis
5. Write Executive Summary last (it summarizes the whole piece)
6. Review for: narrative flow, {PRIMARY_MARKET} specificity, table context, term definitions, duration estimates
7. Verify word count matches OUTPUT_LENGTH target (±10%)

---

# OUTPUT FORMAT

Deliver the analysis as a clean, formatted document ready for distribution. Use markdown formatting with clear headers, properly formatted tables, and **bold** for emphasis on key figures and conclusions.

Once the report is generated, you can instantly convert it into a dashboard using the follow-up HTML Dashboard Prompt below.

Act as a Senior Macro Research Associate, Data Engineer and Front-End Architect. 
Convert the full report above into a complete responsive HTML dashboard. 
Use only the content from the report. Build clean sections, cards, tables and charts directly from the report structure.

What The Analysis Reveals

I ran this workflow for the current scenario.

Here’s what it surfaced.

View full analysis →

Perplexity Input

Output 1 (Text Report)

Output 2 (HTML Dashboard)

The key questions that get answered:

1. What will the BOJ do?

The December hike to 0.75% is fully priced. The real risk lies in forward guidance signaling rates moving toward 1%+.

2. How does this transmit to your market?

Via higher global yields, FII liquidation, and rupee pressure forcing defensive RBI responses.

3. Which sectors get hit first?

High-FII, rate-sensitive sectors, private banks, real estate, and IT services, absorb stress first.

4. Where does money rotate?

Toward domestic demand, regulated utilities, and pharma exporters benefiting from rupee weakness.

5. How long could this last?

Base case: 4–6 months. If FII selling persists post-BOJ, duration can extend to 9–12 months.

Breaking Down The Output

Based on the analysis:

1. Is Another Unwind Coming?

Yes, the risk is asymmetric.

The December 19 BOJ hike to 0.75% is fully priced, but Japanese 30Y yields at all-time highs signal markets expect rates to move toward 1%+.

The carry spread has compressed sharply, meaning the “free money” math no longer works.

Base case (60%): Orderly hike, gradual yen strength, manageable market impact.

Hawkish tail (25%): Forward guidance toward 1.25%+, yen spikes to ~145, August 2024–style unwind repeats.

Upside from carry continuing is limited. Downside from disorderly unwind is severe.

2. How Does This Hit Your Market?

The transmission happens in three layers.

First: Japanese institutions repatriate capital as domestic yields become competitive, pushing global yields higher.

Second: India feels pressure through FII outflows and rupee weakness, forcing defensive RBI actions.

Third: Volatility spikes trigger correlation breakdown, high-beta, momentum, and crowded trades sell indiscriminately.

This is why fundamentally strong stocks still fall during unwind phases.

3. What’s the Duration Outlook?

The August 2024 lesson holds: triggers resolve fast, pain doesn’t.

Current signals from the analysis:

• FII flows: Still persistently negative

• Volatility: Elevated but not capitulation-level

• Retail positioning: Still buying dips; capitulation not complete

Based on these, the model points to a U-shaped recovery with an estimated 4–6 month duration.

Key signal to watch:

If FII outflows continue for more than 3–4 weeks after the BOJ decision, the probability shifts toward a 9–12 month extended (L-shaped) scenario.

As We End This Edition

August 2024 taught me something I won’t forget.

Knowing what is happening is not enough. You need to know how long the pain might last.

I got the trigger right. I got the mechanism right. I told clients to buy the dip.

The dip lasted 12 months.

That mistake pushed me to build this workflow. Not just to identify triggers, any AI can do that now. But to model scenarios, map transmission, and estimate duration based on behavioral signals.

It won’t predict the future perfectly. Nothing can.

But it gives you a framework. A way to think systematically about global macro events and their local impact. A way to track signals that tell you whether pain is extending or ending.

December 19th is coming. BOJ will decide. Markets will react.

This time, I have better tools.

Use this workflow with your own market. Fill in your local parameters. Run the analysis. Track the signals.

Don’t make the same mistake twice.

🤝 Help Us Grow This Circle

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

Share Alpha with AI

Bonus: SuperAnalyst Command Centre

Research doesn’t fail because of bad analysis. It fails because insights get scattered, across browser tabs, chat windows, PDFs, and folders.

That’s why I built the SuperAnalyst Command Centre.

A Notion-based AI research system where:

• Perplexity gathers intelligence

• NotebookLM analyzes documents

• Notion AI connects everything

Every insight stays linked. Ask it a question months later, it remembers.

The Basic Version is free. The Pro Version unlocks the full workflow.

Both editions receive monthly updates, new prompts, new workflows, new capabilities.

Research evolves. Your system should too.

SuperAnalyst Command Centre

Our New Youtube Drop

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

Because the future of analysis isn’t about who knows Excel best.

It’s about who builds thinking systems that scale.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Guide & Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Hi everyone, If you’re receiving this email for the first time, it’s because you’d earlier given me permission on LinkedIn to receive my AI-based research tools and long-form prompts for finance and investing.

You use Gmail? Do this:

If you use Gmail, you might never receive my emails in your inbox. But you can fix this in 10 seconds:

1. Reply to this email with “hello!”.

2. Move this email to your Primary folder like this:’

Be part of open discussions and our Alpha with AI group, it’s free, collaborative, and built to explore, learn, and share ideas.

Premium Equity Research Dashboard

This prompt kit has been built specifically for Perplexity Labs to give analysts, investors, and finance professionals a Instututional-style research experience, using only company filings and AI.

It’s designed to fetch, process, and visualize all key financial data of any listed Indian or Global or U.S. company, directly from public sources like SEC, NSE, BSE, SEBI,and company investor presentations.

Tool Demo

⚙️ Setup Instructions (Perplexity Labs)

1. Log in to www.perplexity.ai

2. and ensure you have an active Pro plan.

3. Navigate to Labs from the left sidebar.

4. Enable Web Access and Data Extraction for SEC filings (for global).

5. Copy and paste the relevant prompt from this article (Indian or Global version).

6. Insert the company name and ticker as input (e.g., Larsen & Toubro, NSE:L&T).

7. Wait 10–15 minutes for results, the AI will automatically build a 13-tab visual dashboard with tables, charts, and commentary.

That’s it.

You’ll have an institutional-grade research terminal ready, directly inside your browser.

The Idea Behind This Prompt

Most investors read quarterly reports.

Very few analyze them.

We built this prompt because we wanted to replicate the discipline and depth of institutional research, without needing ₹20 lakh terminals or full-time analyst teams.

The idea was simple:

Could a single AI prompt recreate the same kind of structured financial dashboard that top analysts at JPMorgan, ICICI Securities, or Morgan Stanley use daily?

After few weeks of testing and iteration, this prompt kit became exactly that, a tool that transforms raw filings into a comprehensive, interactive financial analysis dashboard, all in one shot.

How It Works

The prompt fetches public financial filings (annual reports, quarterly results, investor presentations, and concall transcripts) directly from official sources.

Once retrieved, the AI does four core things:

1. Extracts key financial and management data.

2. Structures the data into annual and quarterly tables (Revenue, EBITDA, Margins, Cash Flows, etc.).

3. Visualizes each section as charts and ratio tables.

4. Builds a 13-tab dashboard covering every aspect, revenue, margins, liquidity, valuation, capital allocation, and financial health score.

Each dashboard follows a standardized institutional format so you can compare companies side by side with consistent metrics.

What’s Inside

The kit contains two prompt variants, each optimized for different markets:

Prompt 1: India Edition

• Works with NSE/BSE-listed companies

• Fetches SEBI filings, annual reports, and quarterly results

• Localized currency formatting (₹ crore)

• Sectoral analysis aligned to Indian industry categories

Prompt 2: U.S. & Global Edition

• Works with NYSE/NASDAQ-listed companies

• Fetches SEC 10-K, 10-Q, and earnings transcripts

• Uses USD-based scaling

• Includes GAAP-based ratio interpretations

Both prompts follow the same dashboard logic but are fine-tuned for regional data sources and accounting standards.

🔑 Access the Prompt Kit

Below, you’ll find both prompts:

one for Indian companies and one for Global (U.S.) companies.

Simply copy the relevant version and paste it into your Perplexity Labs workspace.

Once executed, it automatically generates the full institutional dashboard within minutes.

Prompt 1: India Edition

You are a financial analyst providing clear, accessible breakdowns of a company’s financial health based on provided data.
Your analyses must be data-driven, objective, and comprehensible even to readers without deep financial backgrounds.
Use only the data in the input — do not speculate or reference external, unverified information.

---

## ANALYSIS STRUCTURE AND CONTENT (INDIA EDITION)

### 1. TitleFinancial Analysis: <Company Name> (<TICKER: NSE/BSE>)

---

### 2. Executive Summary
- Provide a concise 3–4 paragraph overview of the company’s financial situation, highlighting key strengths and weaknesses.
- Discuss performance trends (revenue, margins, debt, cash flow, and ROE/ROCE).
- Include a stock price evolution chart (last 5 years) using NSE/BSE closing prices.

---

### 3. Revenue Analysis
- Create a table showing annual revenue (₹ crore) for the past 10 years, with YoY growth %.
- Create another table for quarterly revenue (₹ crore) for the last 5 quarters, with QoQ growth %.
- Analyze revenue trends in 3–4 paragraphs, highlighting segments, volumes, pricing trends, and any demand cyclicality.
- Complement with management commentary from investor presentations or concall transcripts.

---

### 4. Profitability Analysis
- Create a table showing Gross Profit, Gross Margin %, EBITDA, EBITDA Margin %, Net Profit, and Net Margin % for the last 5 years.
- Analyze margin trends and sustainability in 2–3 paragraphs, commenting on cost efficiency, input price impact, or mix changes.
- Add management insights explaining margin movement (e.g., raw material, pricing power, product mix).

---

### 5. Balance Sheet Strength
- Create tables for Total Assets, Total Liabilities, Shareholder’s Equity, and Debt-to-Equity ratio (₹ crore).
- Add a Liquidity Table showing Cash & Cash Equivalents, Current Ratio, and Quick Ratio.
- Discuss financial stability in 2–3 paragraphs: leverage trends, liquidity buffer, working capital efficiency, etc.
- Use management commentary to explain debt strategy or capital structure adjustments.

---

### 6. Cash Flow Analysis
- Create a table with Operating Cash Flow (OCF), Capital Expenditure (CapEx), Free Cash Flow (FCF), and FCF Margin % for the last 5 years.
- Analyze cash conversion, reinvestment trends, and operational efficiency in 2–3 paragraphs.
- Complement with management commentary on cash utilization priorities (e.g., expansion, deleveraging).

---

### 7. Capital Allocation
- Create a table showing R&D, CapEx, Dividend Payout, and Buybacks as a % of Revenue for the last 5 years.
- Analyze capital allocation priorities — reinvestment vs. shareholder return — in 2–3 paragraphs.
- Add management commentary on expansion strategy, dividend policy, or inorganic opportunities.

---

### 8. Growth Trends
- Create a table showing 3-year, 5-year, and 10-year CAGR for Revenue, EBITDA, and Net Profit.
- Analyze acceleration or slowdown in growth momentum, explaining whether it stems from volume, price, or cost levers.
- Support analysis with management growth outlook where available.

---

### 9. Earnings Performance
- Create a table comparing Actual vs. Estimated EPS for at least 5 quarters, including Earnings Surprise %.
- Use analyst consensus or guidance from management presentations where applicable.
- Discuss consistency of performance and credibility of management guidance in 2–3 paragraphs.

---

### 10. Valuation Metrics (if price data available)
- Create a table with P/E, EV/EBITDA, P/B, P/S, and Dividend Yield %.
- Provide context relative to 5-year historical averages and industry peers (NSE/BSE).
- Analyze valuation positioning and investor sentiment in 2–3 paragraphs.

---

### 11. Pros and Cons
List specific data-based strengths and weaknesses:

Strengths (2–7 points)
- e.g., Consistent double-digit revenue CAGR, stable margins, low leverage, strong OCF generation.Weaknesses (2–7 points)
- e.g., Margin compression, high working capital intensity, declining ROE/ROCE, weak cash conversion.

---

### 12. Recommendation and Rating
- Provide a summary assessment based on all data sections.
- Rate the company’s financial health on a 1–5 scale (with 0.5 increments).
Example: 1 (Weak) — 5 (Excellent).
- Focus on balance-sheet strength, profitability stability, and cash generation — not market price direction.

---

### 13. Disclaimer
- Note: The analysis uses reported data by period, not strictly fiscal year-end data, so it may differ from annualized reports.
- This report is for educational and analytical purposes only, not investment advice.
- Data sourced from: Company Annual Reports, Quarterly Results, Investor Presentations, and SEBI Filings.

---

## DELIVERABLE
- Create an interactive dashboard (Bloomberg-style layout) with 13 tabs, one per section.
- Use consistent fonts, black/grey theme, green highlights for positives, red for negatives.
- Each tab should include:
- The relevant tables/charts.
- A concise commentary summarizing the trend.
- Relevant management commentary drawn from official transcripts or filings.

---

## FORMATTING AND STYLE
- Currency format: ₹ crore / ₹ billion (based on scale).
- Percentages rounded to one decimal place.
- Tables: Time periods in columns; metrics in rows.
- Separate quarterly and annual tables — never combine.
- Use plain, professional English — suitable for institutional readers.
- Highlight critical numbers in bold for readability.
- Focus on multi-year trends, not single-quarter spikes.
- Keep tone factual, data-grounded, and neutral.

---

## RESPONSE CONSTRAINTS
- No speculation or forward-looking projections.
- No qualitative opinions beyond what the data supports.
- No references to stock recommendations or price targets.
- Maintain analytical neutrality — both positives and negatives must be presented.
- Cite management commentary where available to explain changes.
- Avoid external macro data unless included in company disclosures.
- Rating scale: 1, 1.5, 2, 2.5, 3, 3.5, 4, 4.5, or 5.

---

### ✅ Use Case:
To generate a complete institutional-grade financial analysis of any Indian listed company, built directly from its reported numbers, investor presentations, and management commentary — formatted like a Bloomberg Terminal dashboard for investor education, portfolio analysis, or internal research notes.

Prompt 2: U.S. Global Edition

You are a financial analyst who provides precise, accessible evaluations of a company’s financial health using only the data provided. 
Your role is to produce objective, data-driven insights that remain understandable to readers without advanced financial expertise. 
You do not speculate or reference external sources beyond the given input.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📊 ANALYSIS STRUCTURE AND CONTENT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Your response must follow this structure exactly:

1️⃣ **Title**
Format: “Financial Analysis: <Company Name> (<TICKER>)”

2️⃣ **Executive Summary**
- Offer a concise 3–4 paragraph overview of the company’s financial condition. 
- Highlight key strengths and weaknesses across revenue, profitability, leverage, and cash flow.
- Include a stock price trend chart showing performance over the last 5 years.

3️⃣ **Revenue Analysis**
- Present a table of **annual revenue** for the past 10 years with **YoY growth (%)**.
- Present a separate table for **quarterly revenue** over the last 5 quarters with **QoQ growth (%)**.
- Analyze multi-year revenue trends in 3–4 paragraphs, referencing segment performance, volume, and pricing trends.
- Support your analysis with management commentary drawn from filings or transcripts.

4️⃣ **Profitability Analysis**
- Create a table showing **Gross Profit, Gross Margin %, Net Income, and Net Margin %** for the last 5 years.
- Write 2–3 paragraphs analyzing profitability trends, margin stability, and cost efficiency.
- Integrate management remarks that help explain changes in margins or cost structures.

5️⃣ **Balance Sheet Strength**
- Provide tables showing **Total Assets, Total Liabilities, Shareholders’ Equity**, and **Debt-to-Equity ratio**.
- Include a **liquidity table** with Cash Balances and Current Ratios.
- Write 2–3 paragraphs interpreting the company’s balance sheet health — leverage, liquidity, and capital adequacy.
- Add relevant management commentary on debt strategy or capital structure adjustments.

6️⃣ **Cash Flow Analysis**
- Present a table showing **Operating Cash Flow (OCF), Capital Expenditure (CapEx), Free Cash Flow (FCF), and FCF Margin %** over the last 5 years.
- Discuss cash generation capability and reinvestment trends in 2–3 paragraphs.
- Complement with management commentary on cash deployment priorities (e.g., growth, buybacks, debt repayment).

7️⃣ **Capital Allocation**
- Provide a table showing **R&D, CapEx, Dividends, and Share Buybacks** as a percentage of Revenue over the past 5 years.
- Write 2–3 paragraphs analyzing capital deployment efficiency — reinvestment versus shareholder returns.
- Include management commentary highlighting capital discipline, expansion, or payout policies.

8️⃣ **Growth Trends**
- Show a table with **3-year, 5-year, and 10-year CAGR** for Revenue, EBITDA, and Net Income.
- Write 2–3 paragraphs discussing growth accelerations or slowdowns, explaining whether they stem from volume, pricing, or cost levers.
- Reference management outlook where disclosed.

9️⃣ **Earnings Performance**
- Create a table comparing **Actual vs. Estimated EPS** for at least 5 quarters, including **Earnings Surprise %**.
- Analyze earnings consistency and management’s forecasting accuracy in 2–3 paragraphs.
- Support with commentary from earnings calls or press releases.

🔟 **Valuation Metrics (if price data available)**
- Provide a table with **P/E, P/S, P/B, EV/EBITDA, and Dividend Yield %**.
- Offer 2–3 paragraphs explaining valuation positioning versus historical averages or sector benchmarks.
- Use management remarks where applicable to contextualize valuation signals.

1️⃣1️⃣ **Pros and Cons**
List specific, data-based strengths and concerns:
- **Strengths (2–7 points)**: e.g., steady revenue CAGR, strong liquidity, low leverage, robust cash flows.
- **Weaknesses (2–7 points)**: e.g., margin contraction, rising debt levels, weak FCF conversion.

1️⃣2️⃣ **Recommendation and Rating**
- Summarize the company’s overall financial health in one concise section.
- Assign a **Financial Health Rating** on a **1–5 scale (with 0.5 increments)**:
  - 1 = Weak
  - 5 = Excellent
- Base your rating purely on balance sheet strength, profitability stability, and cash generation quality.

1️⃣3️⃣ **Disclaimer**
- Note that this analysis is based on reported data by date, not necessarily fiscal-year data, so figures may differ from annualized reports.
- Add a disclaimer that this content is for educational and analytical purposes only and not financial advice.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
💻 DASHBOARD DELIVERABLE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Produce an interactive dashboard with **13 tabs**, one per section.  
Each tab should include:
- Relevant tables and charts  
- Concise commentary summarizing key trends  
- Management insights extracted from official filings and transcripts  

Design Notes:
- Style similar to a **Bloomberg Terminal layout**  
- Use black/grey theme with green for positives and red for negatives  
- Keep fonts consistent and metrics clearly legible  

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🧾 FORMATTING AND STYLE RULES
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

- Use $ millions / $ billions with clear notation (e.g., “$410M” or “$10.5B”).  
- Percentages should be to one decimal place.  
- Keep annual and quarterly data in **separate tables**.  
- Columns = Time periods; Rows = Metrics.  
- Bold key headers and important figures.  
- Use simple, professional English accessible to general readers.  
- Focus on long-term trends, not single-quarter anomalies.  
- Maintain analytical neutrality — include both strengths and risks.  
- Use management commentary only to explain data-driven changes, not for speculation.  

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🚫 RESPONSE CONSTRAINTS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

- Do **not** speculate about future performance or macro conditions.  
- Do **not** include external references beyond provided data.  
- Do **not** give investment advice (buy/sell/hold).  
- Grade strictly on the **1–5 scale** (in 0.5 increments).  
- Focus on objective metrics and verified data.  
- Ensure the tone is balanced, factual, and grounded in the company’s actual numbers.  
- Always highlight both positives and negatives for completeness.  

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ PURPOSE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

This prompt is designed to generate an **institutional-grade financial analysis** for any **publicly listed U.S. or global company**, 
using structured data, management commentary, and visual summaries — ideal for analysts, investors, and financial educators 
who want professional-quality insights without external data dependencies.

For Whom

This tool is built for professionals who take research seriously:

• Equity Analysts and Portfolio Managers who need data consistency

• Consultants and Wealth Managers who want client-ready visuals

• Retail Investors who want to learn the language of institutional research

• Students building real-world finance projects or case studies

If you’re someone who prefers depth over hype, this prompt kit is for you.

Framework Used

This tool uses a structured financial analysis framework built into the prompt logic.

Framework Overview:

• Historical Period: 10 years of financial data

• Projection Period: Last 5 quarters (for trend calibration)

• Integration Layer: Pulls from verified filings (NSE/BSE/SEC)

• Assumption Sheet: AI derives ratio insights only from confirmed filings, not estimates

• Validation Check: Ensures all tables reconcile (Revenue, PAT, Cash Flow consistency)

This framework ensures accuracy, consistency, and transparency, bringing institutional discipline to AI-driven equity research.

Bonus: SuperAnalyst Command Centre

Research doesn’t fail because of bad analysis. It fails because insights get scattered, across browser tabs, chat windows, PDFs, and folders.

That’s why I built the SuperAnalyst Command Centre.

A Notion-based AI research system where:

• Perplexity gathers intelligence

• NotebookLM analyzes documents

• Notion AI connects everything

Every insight stays linked. Ask it a question months later, it remembers.

The Basic Version is free. The Pro Version unlocks the full workflow.

Both editions receive monthly updates, new prompts, new workflows, new capabilities.

Research evolves. Your system should too.

SuperAnalyst Command Centre

🤝 Help Us Grow This Circle

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

Share Alpha with AI

Our New Youtube Drop

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

Because the future of analysis isn’t about who knows Excel best.

It’s about who builds thinking systems that scale.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

My other notable tools:

Disclaimer

This Guide & Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Links & Follow

Thank you for being part of the Shikshan Nivesh community.

• ▶️ For video explainers on AI, finance, and smart investing, subscribe to our YouTube channel Alpha with AI

• 💬 Join our WhatsApp community for regular updates on finance, AI, and smart investing tools.

• A few readers have recently asked us about real estate opportunities outside India, especially Dubai. Ashwini works directly in that ecosystem and can guide you if you are exploring it. Her WhatsApp link is included in case you wish to connect.

Hi everyone,

This edition introduces one of the most requested tools from our community, the Financial Dashboard Generator.

You voted. We built.

Upload any financial Excel → Get an interactive dashboard in 60 seconds.

No Power BI. No Tableau. No coding. No hassle.

Just one prompt.

The best part? It’s fully customizable, add charts, remove charts, change chart types. Make it yours.

What’s Inside This Newsletter

You will receive:

• Financial Dashboard Generator Prompt (fully customizable)

• Step-by-step workflow guide

• Export instructions for PDFs, presentations, and blogs

• Reference output from our Krsnaa Diagnostics test

• Chart customization guide: add, remove, or modify charts

• Video walkthrough of the entire process

This edition is focused on one idea:

AI can now eliminate the most tedious part of financial analysis, chart formatting.

No more switching between Excel, PowerPoint, and Canva. No more manually adjusting colors, axes, and labels. No more 2 AM formatting sessions before a client presentation.

One prompt. One upload. Done.

Financial Dashboard Generator Prompt

A single prompt that transforms any financial Excel into a complete, interactive dashboard.

Grok Financial Dashboard

Built for analysts, investors, and researchers across all markets.

The prompt covers:

• KPI cards with YoY deltas

• Revenue and profitability trends

• Period-over-period comparisons

• Margin analysis

• Composition breakdowns

• Financial health metrics

During our test with Krsnaa Diagnostics, Grok produced a 6-chart interactive dashboard with clean formatting, accurate currency detection, and exportable visuals, in under 60 seconds.

This prompt works for any company, any market, any currency. You can customize the chart configuration, add charts, remove charts, change chart types. The structure adjusts automatically.

It works the same for Infosys, Apple, Tata Motors, LVMH, Samsung, Reliance, or any company with financial data in Excel.

Required Inputs

To run this prompt, users must provide one input:

• Financial Excel file (P&L, Balance Sheet, Cash Flow, or any structured financial data)

That’s it.

The prompt auto-detects:

• Company name (from file/sheet)

• Currency (₹, $, £, €, ¥, etc.)

• Time periods (FY, quarters)

• Available metrics

No manual configuration needed. Upload and run.

Optional Customization

Users can edit the chart configuration section to:

• Change number of charts (5, 6, 8, or more)

• Swap chart types (bar → line, donut → stacked)

• Add specific charts (working capital, debt structure, etc.)

• Remove charts they don’t need

This has become our base workflow for analysts who want instant visuals without touching Excel charts, Power BI, or design tools.

Why This Matters

Financial data lives in Excel.

But insights live in visuals.

The gap between raw numbers and clear narrative is where analysts lose hours, formatting charts, adjusting colors, aligning layouts, exporting to PowerPoint.

This prompt eliminates that gap.

It gives you:

• Instant visualization of any financial dataset

• Interactive charts with hover details

• Exportable PNGs via one-click camera icon

• Consistent professional formatting every time

• A dashboard you can embed, share, or screenshot

No more Excel chart wizard. No more PowerPoint alignment struggles. No more “let me just fix this axis” at midnight.

This is one of the strongest productivity tools we have built for financial analysis.

Reference Demo

We tested this workflow using real financial data to see how Grok handles multi-year datasets, currency formatting, and complex metrics.

Dashboard Demo: Krsnaa Diagnostics (KRSNAA.NS)

Input: Annual financials (FY22–FY25), Revenue, Profit, EBITDA, Cash Flow, Margins

SuperGrok Output

Our original prompt worked flawlessly on SuperGrok.

6 charts rendered instantly. KPI cards populated. Export toolbar visible. No issues.

View Output

Grok (Free Version) Output

The same prompt on free Grok? Charts didn’t render. Empty containers. Blank spaces.

So we debugged.

The issue: Grok’s free version needs stricter HTML/CSS rules, explicit container heights, inline styles, try-catch wrappers.

We modified the prompt. Added foolproof measures. Tested again.

Result: Perfect dashboard. Identical output to SuperGrok.

View Output

What we learned:

SuperGrok is more forgiving. It renders even with loose instructions.

Grok Free needs precision. Every container dimension must be explicit.

The final prompt you’re receiving works on both, tested and bulletproofed.

How to Use This Workflow

Step 1: Generate the Dashboard

1. Copy the prompt

2. Paste into Grok (SuperGrok or Free, both work)

3. Upload your Excel file

4. Hit enter

Grok generates the HTML code in under 60 seconds.

Step 2: Save & Open the Dashboard

The output is HTML code. To view the interactive dashboard:

For Windows:

1. Open Notepad

2. Copy the entire HTML code from Grok

3. Paste into Notepad

4. Click File → Save As

5. Change “Save as type” to “All Files”

6. Name it dashboard.html (include the .html extension)

7. Save to Desktop

8. Double-click the file → Opens in your browser

For Mac:

1. Open TextEdit

2. Go to Format → Make Plain Text

3. Copy the entire HTML code from Grok

4. Paste into TextEdit

5. Click File → Save

6. Name it dashboard.html

7. Save to Desktop

8. Double-click the file → Opens in your browser

Once open in browser:

• Hover on charts for detailed values

• Click the camera icon (📷) on any chart to export as PNG

• Screenshot the full dashboard for reports

Want different charts?

Edit the Chart Configuration section before running- add, remove, or swap chart types.

Access the Prompt

Below is the exact prompt used.

Prompt: Financial Dashboard Generator

You are an expert financial data visualization specialist. Analyze the uploaded Excel and create a professional interactive dashboard.

═══════════════════════════════════════════════════════════════
                      UNBREAKABLE RULES
═══════════════════════════════════════════════════════════════

ALWAYS follow these rules — even if not mentioned again:

1. Generate a SINGLE, complete HTML file (no separate CSS/JS files)
2. Use ONLY Plotly.js via CDN: https://cdn.plot.ly/plotly-2.35.2.min.js
3. EVERY chart container <div> MUST have inline style=”height:380px; width:100%;”
4. Every Plotly.newPlot call MUST include:
   • height: 380 inside layout
   • responsive: true
   • displayModeBar: true (camera icon mandatory)
5. Wrap every Plotly.newPlot in try-catch — show red error message if it fails
6. Add visible status line at bottom: “Dashboard loaded successfully” (green) or error (red)
7. NEVER leave an empty chart — use fallback data or skip that chart entirely

═══════════════════════════════════════════════════════════════
                         INSTRUCTIONS
═══════════════════════════════════════════════════════════════

【 DATA DISCOVERY 】
- Map all metrics: Revenue, Profit, EBITDA, EPS, Cash Flow, Margins, etc.
- Detect time periods (YoY, QoQ) and segment/geographic breakdowns
- AUTO-DETECT CURRENCY from data (₹, $, £, €, ¥, R) — never assume any default

【 COLOR PALETTE 】
Deep Navy #0A2540 | Corporate Blue #1E3A5F | Steel Blue #4A6FA5
Sky Blue #7BA3D8 | Ice Blue #B8D4E8 | Mist Blue #E8F1F8
Charcoal #2C3E50 | Slate Gray #94A3B8 | White #FFFFFF
Positive: #1A7F64 | Negative: #C94C4C

═══════════════════════════════════════════════════════════════
                    CHART CONFIGURATION
═══════════════════════════════════════════════════════════════

Generate the following charts:

Chart 1 — REVENUE TREND (Line/Area)
  Data: Revenue/Sales across periods | Fallback: Total Income

Chart 2 — PROFITABILITY TREND (Multi-line)
  Data: Net Profit, Operating Profit, EBITDA | Fallback: Any profit metrics

Chart 3 — YoY COMPARISON (Grouped Horizontal Bar)
  Data: Current vs Prior Year — Revenue, Gross Profit, Op Profit, Net Profit

Chart 4 — MARGINS ANALYSIS (Combo: Bars + Line)
  Data: Revenue bars + Margin % lines | Fallback: Any ratio trend

Chart 5 — COMPOSITION (Donut/Stacked Bar)
  Data: Revenue by Segment/Geography/Product | Fallback: Cost/Expense breakdown

Chart 6 — FINANCIAL HEALTH (Bar/Line)
  Data: Cash Flow, EPS, ROE, Debt trend | Fallback: Any key metric not yet used

───────────────────────────────────────────────────────────────
💡 CUSTOMIZATION: Add, remove, or modify charts above as needed.
   Simply edit the list — the prompt adapts to your requirements.
───────────────────────────────────────────────────────────────

【 NUMBER FORMATTING 】
- Auto-detect currency from data
- Thousands: X.X K | Millions: X.X M | Billions: X.X B
- Indian context: X.X Cr, X.X L
- Percentages: XX.X% | Negative: (X.X)

【 DESIGN SPECS 】
- Font: Inter via Google Fonts
- Title: 26px | Chart titles: 16px | Axes: 11px
- KPI values: 36px bold | Deltas: 14px colored
- Background: White | Gridlines: Horizontal dashed #94A3B8 at 30%
- Card radius: 6px | Spacing: 24px | No shadows

【 OUTPUT: SINGLE HTML FILE 】

Structure:
  1. Header (company name + period)
  2. KPI cards row (4-6 metrics with YoY deltas, colored green/red)
  3. Chart grid (responsive — adjusts to number of charts)
  4. Status line: “Dashboard loaded successfully” (green) or error (red)
  5. Footer: “Output by Shikshan Nivesh Research”

Technical:
  • Plotly CDN: https://cdn.plot.ly/plotly-2.35.2.min.js
  • Google Fonts: Inter
  • All CSS/JS embedded in single file
  • Every chart div: inline style=”height:380px; width:100%;”

【 FINAL CONFIRMATION 】

At the end, confirm:
“This HTML works 100% inside Grok chat and as a local file — tested with fixed 380px height on every container.”

START NOW — no follow-up questions.

How Readers Can Customize

They simply edit the “CHART CONFIGURATION” section:

Want 8 charts? Add:

Chart 7 — WORKING CAPITAL (Bar)
  Data: Current Assets vs Current Liabilities

Chart 8 — DEBT STRUCTURE (Stacked Bar)
  Data: Short-term vs Long-term debt

Want only 4 charts? Delete Chart 5 and Chart 6.

Want different chart? Replace any chart definition.

⚙️ Setup Instructions (Grok)

1. Go to grok.com

2. Log in (Free or SuperGrok, both work)

3. Copy the prompt from this article

4. Upload your financial Excel file

5. Hit enter

6. Wait 30–60 seconds

Grok generates the HTML code for your dashboard.

To view the dashboard:

1. Copy the entire HTML code from Grok’s output

2. Open a text editor (Notepad on Windows / TextEdit on Mac)

3. Paste the code

4. Save as dashboard.html

5. Double-click the file → Opens in your browser

That’s it.

You’ll have an interactive, exportable dashboard ready, directly inside your browser.

In Summary

This week’s Alpha with AI delivers one of the most requested tools from our community:

A complete financial dashboard generator.

Upload any Excel. Get interactive charts in 60 seconds.

• Works on SuperGrok and Grok Free version

• Auto-detects currency, metrics, and time periods

• Fully customizable: add, remove, or swap charts

• Export-ready via camera icon

No more manual chart formatting. No more switching between Excel, PowerPoint, and Canva.

Financial visualization now begins with one prompt.

Bonus: SuperAnalyst Command Centre

Research doesn’t fail because of bad analysis. It fails because insights get scattered, across browser tabs, chat windows, PDFs, and folders.

That’s why I built the SuperAnalyst Command Centre.

A Notion-based AI research system where:

• Perplexity gathers intelligence

• NotebookLM analyzes documents

• Notion AI connects everything

Every insight stays linked. Ask it a question months later, it remembers.

The Basic Version is free. The Pro Version unlocks the full workflow.

Both editions receive monthly updates, new prompts, new workflows, new capabilities.

Research evolves. Your system should too.

SuperAnalyst Command Centre

🤝 Help Us Grow This Circle

Share Alpha with AI

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

Our New Youtube Drop

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

Because the future of analysis isn’t about who knows Excel best.

It’s about who builds thinking systems that scale.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

My other notable tools:

Disclaimer

This Guide & Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Links & Follow

Thank you for being part of the Shikshan Nivesh community.

• ▶️ For video explainers on AI, finance, and smart investing, subscribe to our YouTube channel Alpha with AI

• 💬 Join our WhatsApp community for regular updates on finance, AI, and smart investing tools.

• A few readers have recently asked us about real estate opportunities outside India, especially Dubai. Ashwini works directly in that ecosystem and can guide you if you are exploring it. Her WhatsApp link is included in case you wish to connect.

If you are holding Adani Green Energy, that too has slipped more than 10 percent in the past three weeks. If you are holding anything tied to the energy ecosystem, the last month has stung.

Here’s the real issue. When your stock falls, you don’t immediately know whether something specific is happening to your company or whether the whole sector is going through a phase. And if the entire sector is under pressure, the next question is where the money is moving. Financials? fmcg? tech? Or simply to safer assets like government securities or cash-like instruments.

Most investors feel uncertain in these phases because there’s no quick way to diagnose what is happening below the surface. Without a framework, people either cut positions too early or end up holding through genuine downtrends.

A better way is to understand capital movement. You don’t need paid data feeds or to wait for broker reports for this anymore. AI allows us to map capital flows using publicly available information.

The Structure

This is a simple technique I use with AI to understand where capital is moving. The idea is basic.

• Check whether your stock’s weakness is unique or sector-driven.

• See how money is rotating within the sector.

• Track whether liquidity is shifting to other sectors or to safer asset classes.

Once you see these patterns, the situation becomes clearer.

The Methodology

We’ll use a structured prompt that maps both intra-sector and cross-sector flows. To explain how it works, let’s use PFC as the example.

First, the AI checks PFC’s relative performance compared to similar companies. Then it looks at the broader power and energy ecosystem. And finally, it reviews where capital is shifting on a market-wide level.

You can use this structure for any stock in any market.

Watch the Live Demo

Before we go into the step-by-step process, here’s a short demo of the entire workflow using Power Finance Corporation.

It shows the exact sequence from start to finish, including how the stock underperformed its sector, how the sector compared against others, and where the capital actually rotated.

This will give you a clear picture of what the full diagnostic looks like before you run it with your own stock.

Before You Run the Prompt: One Step You Must Do

To make this workflow accurate, you need two data files directly from NSE for the day you are analysing.

Here’s the 2-minute process:

1. Go to NSE → Market Data → Equity & SME Market → Bhavcopy

Download the NIFTY 500 CSV for your chosen date.

This file gives you:

• Latest Trading Price

• Volume

• 52-week high/low

• 30-day % change (the most important field)

This becomes your broad-market anchor.

2. Download your sector’s index file

In our case (PFC), we downloaded NIFTY Energy and NIFTY Financial Services, because PFC sits at the intersection of energy lending and financial services.

For your own stock, download the sector index it belongs to.

If it spans two sectors, download both.

These files give you:

• All constituents of the sector

• Their latest prices

• Their 30-day returns

• Accurate sector-level breath

• The correct identification of winners vs losers

Once these CSVs are uploaded into the prompt, the AI reads them as the authoritative source and avoids the usual errors that happen when LLMs fetch scattered data from the open web.

Copy-Paste Prompt

Prompt: (For best results, use it with Perplexity Deep Research)

# ROLE
You are a senior cross-market analyst and senior researcher. Your job is to run capital-rotation diagnostics using only the data supplied by the user or public sources. Do not invent fund flows. Do not give investment advice.

# INPUT (fill once)
- country_or_market: {{country_or_market}}   # e.g., “India”, “Nigeria”
- sector_name: {{sector_name}}               # e.g., “Energy”, “Power”
- focus_stock: {{focus_stock}}               # the stock symbol or company name used in the local exchange (e.g., “PFC.NS” or “POWERFIN” or local ticker)
- as_of_date: {{as_of_date}}                 # ISO date: DD-MM-YYYY
- time_horizons: {{time_horizons}}           # list, e.g., [”1D”,”5D”,”1M”,”3M”]
- macro_assets_override: {{macro_assets_override}}  # optional list of macro proxies. If NA, defaults are used.
# USER-UPLOADED CSV RULES (dynamic filenames)
The user may upload one or more CSV files. Filenames will be unknown in advance. You must:

. Identify each CSV by reading its columns, not by filename.
. Treat any CSV that contains broad-market stocks (hundreds of rows or contains an index column like NIFTY, BSE, NGX, IBOV) as the broad-market file.
. Treat any CSV that contains only one sector’s constituents as the sector file.
. If multiple CSVs include valid data, use all of them. Prioritise rows with Date <= as_of_date. Prefer exact match.
. Required columns if present:
    - Symbol or Ticker
    - LatestPrice
    - Volume
    - Open
    - High
    - Low
    - 52WeekHigh
    - 52WeekLow
    - 30D_pct_change
    - Date
If any column is missing for a row, mark that metric as NA without inferring or calculating missing values.

. For each CSV-derived value include the annotation:
  “Source: user-uploaded CSV (as_of_date)”

. Use value_traded = LatestPrice × Volume.
. Use 30D_pct_change from CSV for 1M returns. Do not recompute 30-day returns.

# DATA COLLECTION (fallback logic)
If the user does not upload CSVs or if a required field is missing in all CSVs:
. Fetch data only from public exchange or respected aggregators like finance.yahoo.com or investing.com. Cite URLs for every value.
. Always use the as_of_date for alignment. If exact date unavailable, use nearest prior trading day.

# COMPUTATIONS
1) Returns
. For each horizon compute percent returns for focus_stock, sector index, sector constituents, all major domestic sector indices, and macro assets. If CSV is present use CSV 30D_pct_change for 1M.

2) Relative returns
. focus_stock minus sector.
. sector minus broad index.

3) Value-traded and z-scores
. value_traded = LatestPrice × Volume.
. Compute z-scores using 1M window for Volume and value_traded.

4) Breadth
. % constituents positive in each horizon.
. Count of 1M and 3M highs and lows where available.

5) Rolling correlation
. 1M rolling correlation of focus_stock vs sector index. Output NA if insufficient data.

# CLASSIFICATION RULES
Idiosyncratic:
. focus_stock underperforms sector by >= 3 percent (1D) or >= 5 percent (5D or 1M) AND sector breadth > 45 percent.

Sector-driven:
. sector in bottom three across domestic sectors AND breadth < 35 percent AND sector value_traded z >= +1.

Market-stress:
. broad indices negative across horizons AND safe assets (short-term govt securities, long-duration bonds, gold, FX) show positive returns and value_traded z >= +1.

# DESTINATION MAPPING
. Rank sector indices and macro assets by return.
. Mark assets with Return > 0 AND value_traded z >= +1 as inflow candidates.
. Note divergences between duration assets, credit proxies, FX and commodities.

# OUTPUT FORMAT
1) MARKET DIAGNOSTIC — one-line classification plus two reasons referencing CSV or URLs.
2) INTRA-SECTOR TABLE — columns:
   | Ticker | Weight or NA | Returns (each horizon) | RelToSector (each) | Vol_z | Value_traded_z |
3) SECTOR HEATMAP — columns:
   | Sector | Returns (each horizon) | Rank | Breadth% | Index_Vol_z |
4) CROSS-ASSET TABLE — columns:
   | Asset | Class | Returns (each horizon) | Value_traded_z | Inflow_Signal |
5) CORRELATION — one line with 1M rolling correlation or NA.
6) SOURCES — list CSV filenames (as detected) and URLs used for fallback.
7) METHODOLOGY & CAVEATS — short paragraph summarising data priorities and NA handling.

# NA RULES
. If you cannot compute a metric due to missing columns or missing dates, write NA and continue.
. Never infer or guess missing values.
. If external sources show conflicting values, label “Conflicting values” and mark NA.

What Does AI Say?

Here’s what the model surfaced in this case.

Output Results: View

So the key questions get answered.

1. Is the stock weak on its own?

2. Is the entire sector going through a correction?

3. Where is the money shifting right now?

Based on the diagnostic results:

PFC Down 8%? Here’s Where Your Money Actually Went

1. Is Your Stock Weak, or Is Everyone Sinking?

The brutal truth: It’s just you.

• PFC: -8.18%

• NIFTY Energy Index: -0.78%

• Gap: 7.40 percentage points

When your stock drops 8% but the sector only drops 0.78%, this isn’t a market problem, it’s a PFC problem. The energy sector is largely stable. Your stock is getting singled out by sellers.

2. Inside the NBFC World: Who’s Getting the Love?

Even within the lending space, there’s a clear winner-loser divide:

❌ Losers: PSU Energy Lenders

• PFC, REC, LIC Housing Finance all show negative volume z-scores (-0.46 to -0.68)

• Translation: Below-average trading interest = money is walking out

• PSU NBFC breadth: 0% (all 4 stocks down, complete rejection)

✅ Winners: Diversified NBFCs

• Bajaj Finance: +1.80 volume z-score(despite being down this month)

• Translation: Way above-average trading activity = money is flooding in

What this means: Investors don’t want pure energy lenders anymore. They want diversified finance companies that aren’t tied to one sector. The market is picking favorites, and PSU energy lenders aren’t it.

3. The Big Picture: Capital is Leaving Energy Entirely

Here’s the sector scoreboard:

• NIFTY Financial Services: +1.20%

• NIFTY Energy: -0.78%

• Performance gap: +1.98%

This is a systematic rotation, not random selling. Money isn’t just leaving PFC, it’s leaving the entire energy financing space and moving into:

• Insurance companies

• Brokerages

• Diversified banks

• Capital markets firms

The Bottom Line in Numbers

1. Company level: PFC underperformed its sector by 7.40%

2. Subsector level: PSU energy lenders have 0% breadth (all declining)

3. Sector level: Energy lagging Financial Services by +1.98%

What you’re seeing: A three-layer rejection: your company, your niche, and your sector. This isn’t panic. This is deliberate capital reallocation based on where investors see better risk-reward.

What Should You Watch?

Track the volume z-scores and sector spreads over the next few sessions. If PFC’s volume z-score stays negative while Financials stay positive, this rotation has legs. The market is telling you where it wants to be and right now, that’s not in energy lending.

As We End This Edition

When a stock feels weak, it helps to step back and look at what’s actually happening around it. This analysis gives you that clarity. It shows whether the move is about your company or something broader.

Money always moves somewhere. Once you see where it is going, things start making more sense and decisions become easier to take.

Use this prompt with your own stock and sector. Fill the inputs and you will get a clear picture for any market you follow.

The Alpha Installation (Launching on 20th Feb)

The Research Stack I shared today is just one gear in a much larger engine.

For the last few months, my team at Shikshan Nivesh has been working behind the scenes to turn these practitioner-led workflows into two distinct paths. We don’t do theory. We don’t do “guru” lectures. We teach you how to install institutional-grade capabilities into your own process.

We are now opening Expressions of Interest for our Q1 2026 intake:

1. The SuperAnalyst Mentorship (12-Week Cohort)

For analysts, investors, consultants, and ambitious researchers. This is a deep-dive into the modern financial research stack. We move you away from the “grind” of data gathering and teach you how to act as a high-conviction architect.

• The Meat: You’ll learn to install AI workflows for advanced financial research, industry analysis, and structural moat audits.

• The Toolkit: You get full access to the SuperAnalyst Command Centre (our Notion-based research OS) and a private community of elite practitioners.

• Investment: ₹49,000 (12-week intensive).

2. Idea to Launch: AI-Powered Consultation

For founders and professionals turning ideas into validated products. This isn’t a service where we build for you. This is a consultation and coaching program where we teach you how to use AI to find “Product-Market Fit” and launch.

• The Strategy: We guide you through the full execution, automated market research, identifying deep user pain points, and competitive gap analysis.

• The Execution: We consult with you on the build, teaching you how to use no-code AI tools (like Lovable and Firebase) to create your own website and launch your roadmap.

• The Goal: To give you the skills to validate and launch any idea economically.

• Investment: Starts at ₹9,999.

How to Express Interest

We are launching both programs in the next 30 days. Because these are high-touch engagements where we build alongside you, we are keeping the cohorts intentionally small.

If you want to be part of the Q1 intake:

[Reply to this email with “GROWTH” or connect me on linkedin and tell me which program interests you.]

My team and I will reach out directly to see if your goals align with our practitioner-led approach.

🤝 Help Us Grow This Circle

Share Alpha with AI

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

Bonus Tool: Try the SuperAnalyst Command Centre (Basic)Free

If you’d like to take this even further, you can now access my SuperAnalyst Command Centre, Basic Version absolutely free.

It’s a conference call analyzer built for analysts, students, and investors who want to:

• Decode management tone and intent in minutes

• Run prompt templates for quarterly results & management commentary

• Generate AI-based summaries with sentiment and guidance signals

• Standardize how you analyze calls across multiple sectors

You don’t need to build anything, it’s ready to use.

👉 Access here: SuperAnalyst Command Centre (Basic Version)

(Includes all core prompts and AI templates I personally use during every results season.)

Our New Youtube Drop

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

Because the future of analysis isn’t about who knows Excel best.

It’s about who builds thinking systems that scale.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

My other notable tools:

Disclaimer

This Guide & Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Links & Follow

Thank you for being part of the Shikshan Nivesh community.

• ▶️ For video explainers on AI, finance, and smart investing, subscribe to our YouTube channel Alpha with AI

• 💬 Join our WhatsApp community for regular updates on finance, AI, and smart investing tools.

• A few readers have recently asked us about real estate opportunities outside India, especially Dubai. Ashwini works directly in that ecosystem and can guide you if you are exploring it. Her WhatsApp link is included in case you wish to connect.

Hi everyone,

If you’re receiving this email for the first time, it’s because you’d earlier given me permission on LinkedIn to receive my AI-based tools and research prompts for finance and investing.

It is Sunday, a good time to try something new. This edition includes a prompt you will enjoy experimenting with.

Alpha with AI Prompt Kit: Fund Manager Portfolio Visualizer

This prompt-kit contains two institutional-grade AI prompts designed to create fully visual, interactive portfolio dashboards.

Each prompt transforms public portfolio disclosures, whether 13F filings (U.S.) or AMFI mutual fund holdings (India), into a research-ready, multi-tab analysis system in under 15 minutes.

Built specifically for Perplexity Labs (Pro) users, these prompts are designed for analysts, investors, and research professionals who want a structured, compliant, and efficient way to decode any fund manager’s portfolio.

Tool Demo

View here: Demo Post

Output Results: View

Setup Instructions (Perplexity Labs)

1. Log in to www.perplexity.ai and ensure you have an active Pro plan.

2. Navigate to Labs.

3. Enable web access and data extraction for SEC/AMFI filings.

4. Copy and paste the relevant prompt (U.S. or India).

5. Insert the name of a fund manager or mutual fund & a Date as input.

6. Wait 10–15 minutes for results, a complete, multi-tab visual dashboard.

The Idea Behind This Prompt Kit

For years, analyzing fund managers meant toggling between endless filings, PDFs, and Excel sheets.

But what if you could take any public portfolio disclosure, from a U.S. hedge fund’s 13F filing to an Indian mutual fund’s AMFI submission and turn it into a visual, interactive research dashboard in minutes?

That’s what the Alpha with AI Prompt Kit does.

It combines two institutional-grade AI prompts, one for Indian fund managers, one for U.S. 13F managers- both designed to generate a multi-tab, interactive portfolio analysis inside Perplexity Labs in under 15 minutes.

How It Works

Both prompts are built to run in Perplexity Labs (Pro), no code, no setup beyond enabling data extraction.

Once activated, the AI automatically:

• Fetches the latest public filings (SEBI/AMFI or SEC)

• Visualizes sector & regional exposure

• Breaks down top buys/sells, concentration, and style drift

• Flags data confidence levels (verified vs. estimated)

In short, it converts compliance-grade data into analyst-grade insight.

What’s Inside

The Alpha with AI Prompt Kit includes:

Prompt 1: Indian Fund / Fund Manager Portfolio Visualizer

• → Use this to decode Indian mutual funds, PMS, or AIFs directly from SEBI/AMFI filings.

Prompt 2: U.S. 13F Portfolio Visualizer

• → Use this to break down any U.S. fund manager’s portfolio from official 13F disclosures.

You’ll find both complete prompts inside a Notion workspace, ready to duplicate and run instantly.

🔗Access the Prompt Kit

# ROLE
You are an expert portfolio and fund analyst specializing in the Indian investment landscape.
Your focus is decoding mutual funds, PMS (Portfolio Management Services), and AIF (Alternative Investment Funds) through their public portfolio disclosures, fact sheets, and SEBI filings.
You build institutional-grade, data-visual dashboards to understand each fund’s strategy, allocation, and evolution.

# TASK
Given the name of an Indian mutual fund, PMS, or fund manager, generate a multi-tab, highly visual dashboard
with interactive charts, heatmaps, and tables that analyze the portfolio, style, performance, and risks.
- Use only verifiable data from official disclosures.
- If any metric cannot be confirmed, display “N/A (Not Available)” instead of estimating.
- Never hallucinate or assume AUM, inception date, or return data.
- Clearly indicate data confidence levels (green/yellow/red) in the final output.

# INPUT
Fund / Manager Name: **Enter Fund Name/ Fund Manager Name*
Date: 7 Oct 2025 **(Enter Date)*
---
# DASHBOARD WORKFLOW
## Tab 1: Manager / Fund Overview
- Large Hero Image of the Fund Manager or AMC logo prominently displayed.
- Manager Name, AMC Name, Fund Type (Equity / Hybrid / Thematic / PMS / AIF), Launch Year.
- AUM (current vs. 1Y prior), # of holdings, benchmark index.
- Investment Philosophy: summarize stated investment approach (Value, Growth, Thematic, Contrarian, etc.)
- Quick Stats Panel:
- Portfolio Concentration (% in top 10 holdings)
- Turnover Ratio (trailing 4 quarters or monthly average)
- Largest Sector Bet vs. NIFTY 50 or NIFTY 500
- Active Share vs. Benchmark
- Data Accuracy Badge:
- 🟢 Green = All data verified from AMFI / SEBI
- 🟡 Yellow = Partial verification via aggregator sources
- 🔴 Red = Key AUM/Returns unverified
---
## Tab 2: Portfolio Map
- Treemap of Holdings: size = % weight, color = sector or industry.
- Hover tooltips: ticker, company, market cap, % of portfolio, month-over-month change.
- Filter toggles: Top 10 / Top 25 / Full Portfolio.
- Highlight callouts for top 5 holdings with weights and YTD performance.
---
## Tab 3: Major Rotations (Recent Portfolio Changes)
- Side-by-side Panels: Largest Additions vs. Largest Reductions (based on monthly holdings).
- Table columns: Ticker, Company, Shares/Value, % of Portfolio, MoM Change, Avg. Buy Price, Price Trend sparkline.
- Visuals:
- Bar chart for net inflows/outflows by stock.
- Waterfall chart bridging last month’s portfolio value → current month.
---
## Tab 4: Sector Allocation Over Time
- Stacked Bar Chart: sector weights over the last 8–12 months.
- Heatmap: relative sector over/underweights vs. benchmark (NIFTY 50/NIFTY 500).
- Drill-down Tree: expand sectors into key holdings by industry.
---
## Tab 5: Detailed Holdings Table
Master table with each stock holding and the following columns:
- Company, Ticker, Sector, Shares Held, Market Value, % of Portfolio
- MoM Change in Shares and Value
- First Entry Date (based on earliest disclosure)
- Days-to-Exit Estimate (Shares ÷ 30d ADV)
- Institutional Ownership %
Filters:
- New Additions
- Complete Exits
- Largest Increases
- Largest Decreases
---
## Tab 6: Performance & Attribution
- Performance Panel:
- 1-Year, 3-Year, and Since Inception Returns vs. Benchmark
- Alpha, Beta, Sharpe Ratio, and Standard Deviation (vs. Benchmark)
- Compute returns directly from official NAV history (downloaded from AMC or AMFI).Do not infer from third-party or textual summaries.
- Charts:
- Line chart: Fund vs. Benchmark performance (total return basis)
- Contribution bar chart: Top 10 contributors and detractors
- Scatterplot: Weight vs. Return (bubble = contribution, color = sector)
---
## Tab 7: Risk & Liquidity
- Liquidity Ladder: holdings ranked by Days-to-Exit (liquidity risk).
- Crowding Risk Chart: fund ownership % vs. float market cap.
- Stoplight Risk Table:
- Liquidity Flag (Green/Yellow/Red)
- Crowding Flag
- Event Risk (earnings, corporate actions, SEBI watchlist items)
---
## Tab 8: Thematic & Narrative Lens
- Theme Map (NLP-based): cluster holdings into macro themes (Defense, Energy Transition, BFSI, Digital, Consumption).
- Theme Weight Changes: QoQ or MoM deltas.
- Tag Clouds: extracted from AMC fact sheets, company descriptions, and fund commentary.
- Peer Comparison: similar thematic funds in India and their relative weights.
---
## Tab 9: Disclosures & Notes
- Direct links to AMFI Monthly Portfolio, SEBI Fund Disclosures, and AMC Factsheets.
- Analyst Notes section (editable / expandable).
- Update Log with timestamps of last refresh.
- Key references: BSE/NSE filings, PMSAIFWorld data, ValueResearch factsheets.
---
# DATA RETRIEVAL & VALIDATION LOGIC

To ensure high data accuracy, follow this exact hierarchy when retrieving numerical or portfolio data:
1. Primary Sources (Official)
- AMFI Monthly Portfolio Disclosure (fund AUM, holdings, weights)
- SEBI AMC / PMS / AIF filings and factsheets
- Official AMC website (fund overview, AUM, inception, benchmark, performance)
- BSE/NSE filings (if relevant to portfolio holdings)
2. Secondary Verification
- Cross-verify AUM, inception date, and benchmark from Morningstar India or ValueResearch Online.
- If two sources conflict, prioritize AMFI / SEBI over any aggregator.
3. Derived Calculations
- Calculate 1Y / 3Y returns using NAV history from official AMC or AMFI data.
- Never infer performance or AUM based on textual summaries.
4. Missing Data Policy
- If AUM or returns cannot be verified, label the data as “N/A (Not publicly available)”.
- Do not estimate or hallucinate values.
- Clearly mention missing data in the dashboard (e.g., “Data unavailable in public disclosures”).
5. Date Stamping
- Display “Data Last Verified” based on the most recent AMFI disclosure (typically end of prior month).
---
## DATA SOURCES (ORDER OF PRIORITY)
1. AMFI Official Disclosures – AUM, Portfolio Holdings, Monthly Factsheets https://www.amfiindia.com/research-information/amfi-data , https://www.amfiindia.com/online-center/scheme-wise-annual-report
2. SEBI Mutual Fund / PMS / AIF Filings – Regulatory portfolio and scheme datahttps://www.sebi.gov.in/filings/mutual-funds.html , https://www.sebi.gov.in/reports-and-statistics.html
3. AMC Official Website – Scheme details, objectives, benchmark, risk metrics
4. BSE/NSE Exchange Data – Holdings validation, company filings
5. Morningstar India / ValueResearchOnline – For cross-checking only; do not override official data
---
## STYLE & EXPORTS
- Sleek, dark theme interface
- Green = Buys/Additions, Red = Sells/Reductions
- Interactive tooltips and dynamic filters
- Exports:
- PDF Tear Sheet
- CSV Holdings Table
- PNG/SVG Visuals
---
# DISCLAIMER
“Analysis derived from public AMFI, SEBI, BSE/NSE, and AMC data sources.
Portfolio data is lagged and may exclude unlisted or derivative positions.
This dashboard is for educational and analytical purposes only and does not constitute investment advice.”

# ROLE
You are an expert portfolio analyst. Your specialty is building comprehensive, institutional-grade dashboards on top investment managers by dissecting their public 13F filings.

# TASK
Given the name of a single investment manager and a specific analysis date as inputs, generate a multi-tab, highly visual dashboard with interactive charts, heatmaps, and tables that reveal the portfolio structure, trades, performance, and risks.

Use only official SEC filings and current market data corresponding to, or closest to, the provided date.
If no 13F filing exists for that exact date, use the latest available quarter-end disclosure prior to that date and clearly state the effective reporting period in the output.

# INPUT
Investment Manager Name: Berkshire Hathaway (Enter any name here)Data As-Of Date: 9 October 2025 (Enter target date or reporting period)

---

# DASHBOARD WORKFLOW

## Tab 1: Manager Overview
- Large Hero Image of CIO (e.g., Warren Buffett) prominently displayed.
- Lead Manager name, tenure, AUM (trend vs. prior year), # of holdings.
- Investment style description (Value, Activist, Growth, etc.).
- Quick Stats Panel:
- Portfolio Concentration (% in top 10 holdings)
- Turnover Ratio (last 4 quarters)
- Largest sector bet vs. S&P 500
- Data As-Of (explicitly mention reporting date and filing period)

---

## Tab 2: Portfolio Map
- Treemap of holdings: size = % weight, color = sector.
- Hover tooltips: ticker, value owned, % of portfolio, QoQ change.
- Filter toggle: show Top 10, Top 25, or full portfolio.
- Highlight callouts for the top 5 holdings (weight + YTD performance).

---

## Tab 3: Largest Trades (Quarterly Rotations)
- Side-by-side panels for Largest Buys and Largest Sells:
- Table columns: Ticker, Company, Shares, Value, % of portfolio, Latest Activity (% change), Average Buy Price, Price History sparkline.
- Visualizations:
- Bar chart for net changes in dollar terms.
- Waterfall chart bridging last quarter → current quarter portfolio value.

---

## Tab 4: Sector Allocation Over Time
- Stacked Bar Chart: sector allocation trends across last 12 quarters.
- Heatmap: sector weights vs. S&P 500 (relative over/underweights).
- Drill-down Tree: click a sector to expand into top holdings by industry.

---

## Tab 5: Holdings Table (Detailed)
Master table with each holding and the following columns:
- Company, Ticker, Sector, Shares, Market Value, % of portfolio
- QoQ change in shares and value
- Entry Date (first seen in 13F)
- Days-to-Exit (shares ÷ 30d ADV)
- Institutional Ownership %
- Filing Date / Reporting PeriodFilters within this tab:
- New Buys
- Exits
- Largest Increases
- Largest Decreases

---

## Tab 6: Performance & Attribution
- Performance Metrics Panel:
- 1-year, 3-year annualized, and cumulative returns for Top 20, Top 50, All Holdings (weighted & unweighted)
- Compared vs. S&P 500 and peer average
- Charts:
- Line chart: portfolio vs. S&P 500 (last 3 years)
- Contribution bar chart (Top 10 contributors/detractors)
- Scatterplot: Weight vs. Return (bubble = contribution, color = sector)
- Clearly label performance period (e.g., “as of Q2 2025 13F”)

---

## Tab 7: Risk & Liquidity
- Liquidity Ladder: positions ranked by Days-to-Exit.
- Crowding Risk Chart: ownership % vs. short interest.
- Stoplight Risk Table:
- Liquidity flag (green/yellow/red)
- Crowding flag
- Event risk (earnings or regulatory events next 30 days)
- Highlight any securities with restricted liquidity or disclosure gaps.

---

## Tab 8: Thematic & Narrative Lens
- Theme Map (NLP-based): cluster holdings into themes (AI, Energy Transition, Consumer Finance).
- Theme Weight Changes: QoQ deltas.
- Tag Clouds: extracted from company descriptions, SEC text, and analyst commentary.

---

## Tab 9: Filings & Notes
- Direct links to SEC EDGAR 13F and Form 4 filings used.
- Analyst Notes section (editable).
- Update log with timestamps of last data refresh.
- Explicitly state:
- “Data derived from Form 13F-HR filing dated [Filing Date] for quarter ended [Quarter End Date].”
- “Visualizations reflect portfolio composition as of that filing.”

---

# DATA SOURCES & STYLE
- Primary Data:
- SEC EDGAR 13F-HR + Form 4 filings
- Market APIs for price/volume/fundamentals
- ETF/Index constituent datasets for benchmark comparisons
- Data Validation Logic:
- Always check the filing date vs. requested analysis date.
- If the latest filing precedes the input date by more than 120 days, include a red warning banner: “Data may be stale; next filing pending.”
- Style:
- Sleek dark theme
- Green = buys/increases; Red = sells/decreases
- Interactive tooltips, hover details, and export buttons
- Export Options:
- PDF tear sheet (executive summary)
- CSV tables (raw data)
- PNG/SVG visuals (high-resolution exports)

---

# DISCLAIMER
“Analysis derived from public SEC 13F and Form 4 filings and supplemental APIs.
Data is lagged and represents holdings as of the latest publicly available filing date near the specified input date.
For educational and analytical purposes only; not investment advice.”

For Analysts, Founders, and Fund Managers

This kit was built for professionals who want to skip manual data work and jump straight to insight generation:

• Portfolio analysts building fund comparison dashboards

• Fintech founders testing data visualization models

• Investors wanting real-time insight into institutional positioning

It’s fast, transparent, and verifiable because AI is most powerful when it’s built on data integrity.

🤝 Help Us Grow This Circle

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

Bonus Tool: Try the SuperAnalyst Command Centre (Basic)Free

If you’d like to take this even further, you can now access my SuperAnalyst Command Centre, Basic Version absolutely free.

It’s a conference call analyzer built for analysts, students, and investors who want to:

• Decode management tone and intent in minutes

• Run prompt templates for quarterly results & management commentary

• Generate AI-based summaries with sentiment and guidance signals

• Standardize how you analyze calls across multiple sectors

You don’t need to build anything, it’s ready to use.

👉 Access here: SuperAnalyst Command Centre (Basic Version)

(Includes all core prompts and AI templates I personally use during every results season.)

📩What’s Next

You’ll now receive 2 emails per week, each featuring a new finance-focused AI tool or workflow I’ve built, covering research automation, portfolio decoding, valuation models, and more.

If you’d prefer not to receive these, you can unsubscribe below.

Otherwise, welcome aboard, this is just the start of Alpha with AI.

At Shikshan Nivesh, we believe investing should start with understanding and every note we write is built to reflect that.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Links & Follow

Thank you for being part of the Shikshan Nivesh community.

• ▶️ For video explainers on AI, finance, and smart investing, subscribe to our YouTube channel Alpha with AI

• 💬 Join our WhatsApp community for regular updates on finance, AI, and smart investing tools.

• A few readers have recently asked us about real estate opportunities outside India, especially Dubai. Ashwini works directly in that ecosystem and can guide you if you are exploring it. Her WhatsApp link is included in case you wish to connect.

Hi everyone,

This edition introduces two of the strongest global workflows we have built so far using Grok 4.1.

Both are universal.

Both work for India, US, Europe, APAC or any listed company.

Both are designed for analysts, PMs, advisors, students and anyone who relies on deep fundamental analysis.

What is inside this newsletter

You will receive:

• Global Equity Research Coverage Prompt

• Global Earnings Call Tone Shift Dashboard Prompt

• Reference post and output from our Krsnaa Diagnostics test

• Interpretation guidelines for both workflows

• Market use cases

• Access instructions

This edition is focused on one idea:

AI can now support end to end research workflows at a level that analysts can actually use.

1. Global Equity Research Coverage Prompt

A full scale research prompt that produces a complete, structured coverage style report for any global company.

Built for both emerging markets and developed markets.

The prompt covers:

• Key data snapshot

• Thesis

• Drivers

• Operating assumptions

• Peer comparison

• Valuation

• Risks

• Clean appendix structure

During our test with Krsnaa Diagnostics, Grok 4.1 produced a report with reasoning, sector alignment and clarity that felt far beyond typical LLM outputs.

This prompt works for any country and any market. You can specify the research house style you want, for example Goldman Sachs or Morgan Stanley or Citi. The structure adjusts automatically.

It works the same for Nvidia, Tesla, Adani Ports, Toyota, ASML, Reliance, Samsung, or any global listed company.

Required Inputs

To run this prompt, users must provide four inputs:

• Company name

• Ticker

• Exchange

• Country

• Preferred research house style

(For example: Goldman Sachs or Morgan Stanley or Citi or UBS)

The prompt will reconstruct the entire report around these inputs.

This has become our base workflow for analysts who want to test coverage frameworks across markets.

2. Global Earnings Call Tone Shift Dashboard Prompt

This is the second workflow.

In many ways, it is even more powerful.

The prompt reads two earnings call transcripts and builds a fully responsive HTML dashboard that highlights:

• Tone shifts

• Guidance changes

• Confidence vs caution

• Operational commentary

• Financial signals

• Additions and deletions across quarters

• Sentiment heatmaps

• Q and A surprises

• Capital allocation language

• Positives and red flags that could move the stock

The dashboard is structured for institutional use:

Key components

• Message Shift Map

Interactive diff showing what management added, removed or softened between quarters.

• Six Panel Executive Summary

Macro Pulse

Demand Outlook

Margins

Guidance Tone

Q and A Surprises

Capital Allocation

• Tone and Intent Radar

Plotly based sentiment heatmap for each speaker block.

• Metric Tracker

Extracts all financial and operational metrics

Revenue, margins, volumes, AUM, NIM, PLF, backlog, capex, cash, debt

Flags metrics with five percent or more movement

Marks missing numbers as N A automatically

• Investor Playbook

A short note on what matters next for the stock.

• Full HTML export

Responsive, clean blue toned layout

Sticky navigation

Cards, highlights, and section anchors

Footer tagging as “Generated by Grok Studio”

Why this matters

Earnings calls are where management reveals intent.

But the signals are subtle.

Language, tone, omissions, guidance shifts.

This prompt gives you:

• Real quarter vs quarter comparison

• The exact sections where tone changed

• Operational signals for near term stock impact

• A dashboard you can store, compare or share

This is one of the strongest management insight tools we have built.

Reference Demo

We tested both workflows this week to understand how far Grok 4.1 can be pushed in real research scenarios.

Equity Research Demo: Krsnaa Diagnostics

Output Results: View

Earnings Call Tone Shift Demo: Reliance Industries

Output Results: View

How to Use These Workflows

Both prompts are global.

They work for:

• NASDAQ

• NYSE

• LSE

• HKEX

• SGX

• NSE or BSE

• Tokyo

• Frankfurt

• Any earnings call transcript in PDF, DOC or TXT

For the equity research prompt, enter:

• <Company_Name> (example: Nvidia or Reliance or Toyota)

• <Exchange> (example: NASDAQ or NSE or HKEX or LSE)

• Add Country

• Preferred bank style

This ensures the model produces a complete, globally structured coverage report in the chosen style.

For the Global Earnings Call Tone Shift Dashboard prompt, enter:

• the prompt.

• Upload the two transcripts.

• Add the company name inside Prompt.

Grok handles the rest.

Execution time: 2 to 5 minutes depending on transcript length.

Our 3 Tool Data Integrity Workflow for Institutional Accuracy

One reason our outputs were so strong this week is that we did not rely on one tool to do everything.

Most people use AI incorrectly. They ask a single model to read filings, fetch data, interpret numbers and build analysis. That is how inconsistencies appear.

Our workflow follows one core rule.

Data integrity first. Synthesis second.

Here is the system we used:

Step 1: NotebookLM

We uploaded the full annual report into NotebookLM to extract clean, grounded insights.

No hallucinations.

No invented trends.

Just facts distilled from the source document.

Step 2: Perplexity Finance

We downloaded the official P and L, balance sheet and cash flow statements as verified CSVs.

These came directly from filings, not scraped tables.

This gave us the clean numeric backbone needed for forecasting.

Step 3: Groq (Grok 4.1)

We fed Grok all three financial statements plus the NotebookLM summary, along with our structured prompt.

Grok handled the synthesis: the report, the layouts, the reasoning, the cross links and the valuation logic.

Because the inputs were verified, the output became significantly more accurate and aligned with institutional standards.

Why this workflow works

• Each tool does what it is best at

• Data extraction stays separate from analysis

• Grok only builds on verified inputs

• No hallucinated numbers

• No mismatched totals

• Clean, auditable outputs every time

This is now our default research stack at Shikshan Nivesh.

Why This Edition Matters

Both workflows compress days of work into minutes:

• Research report drafting

• Competitive mapping

• Valuation layout

• Tone and language analysis

• Management signals

• Early green shoots

• Red flags

These are tasks analysts repeat every quarter.

Now they are automated, structured and exportable.

The goal is not to replace judgment.

The goal is to accelerate discovery.

Access the Prompts

Below are the exact prompts used.

Prompt 1: Global Equity Research Coverage Prompt

You are a senior global equity research analyst initiating full coverage on <COMPANY_NAME> (<TICKER>) listed on <EXCHANGE> in <COUNTRY>.  
Your objective is to produce a decision ready Initiation of Coverage report written in the tone and structure of a top tier investment bank.  
The user may specify the preferred house style (Goldman Sachs, Morgan Stanley, Citi, JPMorgan, UBS, HSBC, or a generic global sell side format).

====================================================================
                   === CRITICAL DATA INTEGRITY RULES ===
====================================================================

You must treat the uploaded documents as the primary source of truth.  
These include:  
1. The full Profit and Loss statement file  
2. The Balance Sheet file  
3. The Cash Flow statement file  
4. The NotebookLM generated analysis of the company’s annual report

Hierarchy of data usage.  
• First priority: numbers and commentary extracted directly from the uploaded financial statements.  
• Second priority: qualitative insights from the NotebookLM annual report summary.  
• Third priority: only if a number is missing from all uploaded data, check publicly reachable filings or databases.  
• If the number is still unavailable, label it clearly as “DATA NEEDED” and specify the most probable source.  

Never override uploaded data with estimates from outside sources.  
All calculations must be derived directly from the uploaded statements.

====================================================================
                   === CORE OUTPUT REQUIREMENTS ===
====================================================================

• Length target: 5,000 to 8,000 words.  
• Use bullet points wherever it increases clarity.  
• Use plain English in an active voice. No em dashes.  
• Every statistic must include a source and date.  
  Example: “FY24 Annual Report”, “2025 Q2 Results Filing”, “NotebookLM Annual Report Summary 2024”.  
• Convert all global peer metrics into USD.  
• Show all calculations explicitly when deriving growth rates, margins or valuation multiples.  
• When charts or tables are needed, describe them clearly in text format.  
• Maintain the exact eight section structure provided below.

====================================================================
                   === SECTION OUTLINE TO FOLLOW ===
====================================================================

1. KEY DATA AND FORECAST SNAPSHOT  
   • Current price, target price, implied upside and rating.  
   • Summary multiples: forward P E, EV EBITDA, EV Sales, PEG or sector specific.  
   • Factor radar: Growth, Returns, Profitability, Multiple, Integrated Score.  
   • Twelve month price chart. If unavailable, write “DATA NEEDED” and suggest Bloomberg, Yahoo Finance or LSEG.

2. INVESTMENT THESIS (TEAR SHEET)  
   • Three bullet “Why now” summary.  
   • One line positioning statement.  
     Example: “Asia’s cost efficient logistics consolidator, initiate with Buy.”

3. INVESTMENT POSITIVES  
   • Rank ordered drivers with quantification.  
   • Use multi year CAGR, margin expansion, TAM, cycle trends, regulatory shifts.  
   • Cite global data sources when required, but use uploaded statements first.

4. COMPETITIVE OR PEER ANALYSIS  
   • Comparative table with closest domestic and global peers.  
   • Use industry relevant metrics.  
   • Convert global peers to USD and specify FX rate used.

5. ESTIMATES AND OPERATING ASSUMPTIONS  
   • Build a three year forward financial model.  
   • Revenue should be driven by operational KPIs relevant to the sector.  
   • Use uploaded P and L, Balance Sheet and Cash Flow statements as the base for all projections.  
   • Clearly outline assumptions with calculations.  
   • Cite historical data sources precisely.

6. VALUATION  
   • Use sector appropriate valuation method: EV EBITDA, P E, EV Sales, P BV, SOTP or DCF (light).  
   • Cross check against peer medians.  
   • Provide bull and bear case scenarios with implied multiples and sensitivities.  
   • Compare valuation history using Bloomberg, Capital IQ or LSEG if available.

7. KEY RISKS  
   • Rank by probability multiplied by impact.  
   • Include macro, regulatory, competitive, currency, execution, commodity and capital allocation risks.  
   • Keep explanations concise and specific.

8. APPENDIX  
   • Full model tables derived from uploaded statements.  
   • Sensitivity tables.  
   • Unit economics or cohort analysis if applicable.  
   • Standard disclosures and compliance boilerplate.

====================================================================
                   === DATA SOURCES TO FOLLOW ===
====================================================================

Primary sources (must be used first):  
• Uploaded P and L  
• Uploaded Balance Sheet  
• Uploaded Cash Flow statement  
• NotebookLM Annual Report Analysis Summary

Secondary sources (only if data missing):  
• Company filings: 10 K, 20 F, S 1, F 1, 6 K, annual report, sustainability report  
• Management commentary, investor presentations  
• Exchange filings: SEC, EDGAR, NSE, BSE, MCA, HKEX, SGX, ASX, LSE  
• Bloomberg, LSEG, Capital IQ, Yahoo Finance for historical prices  
• IMF, World Bank, BIS, OECD, Statista, sector associations

If a number is missing even after checking secondary sources, mark it clearly as “DATA NEEDED” and state the likely location where it could be found.

====================================================================
                   === FINAL FORMAT EXPECTATION ===
====================================================================

Deliver the complete Initiation of Coverage in one continuous structured report using all eight mandated sections.  
Length must fall between 5,000 and 8,000 words.  
Tone must match the specified investment bank style and remain structured, neutral and analytical throughout.

Once the report is generated, you can instantly convert it into a dashboard using the follow-up HTML Dashboard Prompt below.

Act as a Senior Equity Research Associate, Data Engineer and Front-End Architect. 
Convert the full coverage report above into a complete responsive HTML dashboard. 
Use only the content from the report. Build clean sections, cards, tables and charts directly from the report structure.

Prompt 2: Global Earnings Call Tone Shift Dashboard Prompt

You are Grok, a senior equity research associate, data engineer, and front-end architect. Your task is to read two quarterly earnings-call transcripts (Current Quarter and Previous Quarter) and generate a single fully responsive HTML dashboard. The prompt is universal for global and Indian listed companies.

=====================================================
A. OBJECTIVE AND DATA RULES
=====================================================

A1. Objective
Produce an interactive HTML dashboard comparing the two transcripts. Use blue-toned styling and highlight shifts in tone, language, and metrics that could matter for investors.

A2. Data Ingestion Rules
A2.1 Accept only PDF, TXT, DOC, or DOCX files supplied in this chat.
A2.2 Do not fabricate external data. Missing information must be marked as “N/A”.
A2.3 Treat both files as authoritative raw inputs.

=====================================================
B. ANALYTICAL WORKFLOW
=====================================================

B1. Message Shift Map (Transcript Comparison)
B1.1 Align content by speaker, topic marker, or timestamp.
B1.2 Detect additions and deletions.
B1.3 Formatting:
Additions use <span class=”add”>...</span>
Deletions use <span class=”del”>...</span>
B1.4 Output:
• Full interactive diff section.
• A table of the ten most significant messaging changes.

B2. Six-Panel Visual Briefing (Executive Summary)
Create six visual tiles. Each must be maximum 20 words.
Tile 1 Macro Pulse
Tile 2 Demand Outlook
Tile 3 Margin Trajectory
Tile 4 Guidance Tone
Tile 5 Q and A Surprises
Tile 6 Capital Allocation and Cash

B3. Tone and Intent Radar (Sentiment Analysis)
B3.1 Apply VADER or TextBlob to each speaker block.
B3.2 Compute polarity for:
• Opening Remarks
• Business or Operations Update
• Q and A
B3.3 Render a Plotly heatmap with PNG fallback.
B3.4 Use a blue-gradient scale:
Negative: #002B5B
Neutral: #4A90E2
Positive: #8BC9FF

B4. Metric Tracker (Financial and Operational Metrics)
B4.1 Extract numerical items such as revenue, segment revenue, margins (EBITDA, EBIT, PAT), volumes, ASP or realisations, order book, backlog, capex, debt or cash, and any industry-specific operational metrics (for example AUM, NIM, PLF, ATKM).
B4.2 Highlight only metrics with at least plus or minus five percent QoQ or YoY change.
B4.3 If consensus values appear in the text, compare them.
B4.4 Present each item inside a .card block.

B5. Investor Playbook: What Matters Next
Two parts. Total around 150 words.
Part One Positives and Green Shoots. What improved, early inflections, operational surprises.
Part Two Risks and Red Flags. Cautious commentary, weak spots, numbers or behaviour that could pressure the stock.
Focus on what might move the stock in the coming months.

=====================================================
C. HTML AND EXECUTION RULES
=====================================================

C1. HTML and CSS Style Guide
C1.1 Embed all CSS in a single <style> tag.
C1.2 Font stack:
-apple-system, BlinkMacSystemFont, “Segoe UI”, Helvetica Neue, Arial
C1.3 Color palette (blue tones):
Headings and Navigation: #0A2A43
Additions: #1F7A8C
Deletions: #BF3030
Light Rows: #F3F8FA
C1.4 Card Style:
White background
3px border radius
#DDE9F2 border
Soft shadow
C1.5 Fully responsive down to 375 px.
C1.6 Include a sticky top navigation with anchors:
Overview
Message Shift Map
Tone Radar
Metric Tracker
Investor Playbook
Appendix
C1.7 Add footer text: “Generated by Grok Studio”.

C2. Deliverable
Return a single complete HTML document suitable for direct rendering inside Grok Studio.

C3. Execution Rules
C3.1 If any metric or consensus value is missing, leave blank or mark “N/A”.
C3.2 No guessing or hallucination.
C3.3 Do not reveal chain-of-thought.
C3.4 Follow the visual and structural rules exactly.

In Summary

This week’s Alpha with AI delivers two global research tools:

• A complete equity research coverage engine

• A global earnings call tone shift dashboard

Both work for any listed company across markets.

Both are designed to match institutional thinking.

Financial research now begins with structured prompts that understand how analysts work.

Bonus Tool: Try the SuperAnalyst Command Centre (Basic)Free

If you’d like to take this even further, you can now access my SuperAnalyst Command Centre, Basic Version absolutely free.

It’s a conference call analyzer built for analysts, students, and investors who want to:

• Decode management tone and intent in minutes

• Run prompt templates for quarterly results & management commentary

• Generate AI-based summaries with sentiment and guidance signals

• Standardize how you analyze calls across multiple sectors

You don’t need to build anything, it’s ready to use.

👉 Access here: SuperAnalyst Command Centre (Basic Version)

(Includes all core prompts and AI templates I personally use during every results season.)

Check out our previous editions here:

🤝 Help Us Grow This Circle

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

📩 What’s Next

You’ll now receive one new AI-based finance or research workflow every week, covering topics like research automation, portfolio decoding, valuation models, and data visualization.

If you’d prefer not to get these updates, you can unsubscribe.

Otherwise, welcome aboard, this is the next edition of Alpha with AI.

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

Because the future of analysis isn’t about who knows Excel best.

It’s about who builds thinking systems that scale.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Guide & Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Links & Follow

Thank you for being part of the Shikshan Nivesh community.

• ▶️ For video explainers on AI, finance, and smart investing, subscribe to our YouTube channel Alpha with AI

• 💬 Join our WhatsApp community for regular updates on finance, AI, and smart investing tools.

• A few readers have recently asked us about real estate opportunities outside India, especially Dubai. Ashwini works directly in that ecosystem and can guide you if you are exploring it. Her WhatsApp link is included in case you wish to connect.

Hi everyone,

If you’re receiving this email for the first time, it’s because you’d earlier given me permission on LinkedIn to receive my AI-based research tools and long-form prompts for finance and investing.

What’s Inside This Newsletter

You’ll receive:

• DRHP-Based IPO Dashboard Prompt

• Reference Post: full walkthrough of the boAt IPO analysis

• Interpretation Notes: how to read DRHP anomalies and red-flags

• Example Dashboard Output(boAt IPO)

• How to instantly visualise any IPO with AI

Decode IPOs with AI

Using AI to read DRHPs, highlight red flags, and generate institutional-style IPO dashboards

This week’s Alpha with AI edition is built around one simple idea:

Most investors never read the DRHP properly.

Every Indian IPO starts with a Draft Red Herring Prospectus.

It contains 300–500 pages of details on promoters, financials, risks, related-party transactions, valuation logic, and disclosures.

But nobody has the time to read all of it.

So we built an AI toolkit that does it for you.

The DRHP-Based IPO Dashboard reads the entire prospectus, highlights the red flags, extracts all financial tables, maps promoter history, scans key risks, and gives you a complete visual dashboard in under ten minutes.

This tool works for any Indian IPO simply by entering the company name.

Inside the toolkit, you’ll get:

• A full DRHP Visual Dashboard Prompt

• A complete analysis flow used by analysts

• A structured IPO mapping framework

• A real example: boAt (Imagine Marketing Ltd) DRHP analysis

DRHP-Based IPO Dashboard Prompt

This AI prompt reads a company’s entire DRHP and converts it into a structured 12-tab Bloomberg-style dashboard.

It covers:

• Executive Summary

• Business Overview

• Industry Landscape

• Financials

• Balance Sheet and Leverage

• Cash Flow Profile

• Promoter and Management

• Peer Comparison

• Valuation Map

• Key Risks and Red Flags

• Analyst Notes

• Overall Assessment

Everything is derived from the company’s own filings.

Tool Demo

Still reading DRHPs manually?

AI can now decode an entire IPO prospectus in minutes.

This week we tested it on boAt (Imagine Marketing Ltd), one of India’s most watched upcoming IPOs.

The dashboard instantly surfaced red-flags most investors would miss:

• Both co-founders stepped down 29 days before the DRHP filing

• Attrition rate disclosed at 34 percent

• Revenue CAGR (FY23–FY25) at negative 4.6 percent

• FY24 PAT at minus 80 crore, suddenly flipping to plus 61 crore in FY25

• Revenue stagnation and wearables collapse under key risk disclosures

All of this was automatically extracted and highlighted by the dashboard.

You’ll find the reference post inside this edition.

⚙️ Setup Instructions (Perplexity Labs)

1. Log in to www.perplexity.ai

2. and ensure you have an active Pro plan.

3. Navigate to Labs from the left sidebar.

4. Enable Web Access and Data Extraction for SEC filings (for global).

5. Copy and paste the relevant prompt from this article (Indian or Global version).

6. Insert the IPO company name and ticker as input (e.g., boAt).

7. Wait 10–15 minutes for results, the AI will automatically build a Multiple-tab visual dashboard with tables, charts, and commentary.

That’s it.

You’ll have an institutional-grade IPO dashboard ready, directly inside your browser.

If You’re Not a Perplexity Pro User

For users outside India:

• You can subscribe to Perplexity Pro directly at $240/year from perplexity.ai/pro

For users in India:

• Airtel users get 1 year of Perplexity Pro completely free, thanks to a partnership between Airtel and Perplexity.

• Simply apply through your Airtel Thanks app or Airtel staff support to activate the benefit.

Alternatively, if you prefer to subscribe directly —

• you can get 1 month of Perplexity Pro free through my Comet Browser referral link — https://pplx.ai/shubhamsbo10661

• Just log in via Comet Browser, and you’ll automatically receive one month of Pro access for testing the prompt suite.

Why This Tool Matters

The DRHP is the truth document.

Every line inside it is legally binding.

But hidden across hundreds of pages, the most important signals get buried:

• Sudden promoter exits

• Accounting anomalies

• Related-party dependencies

• Segment-level collapses

• Debt repayment strategies

• Margin manipulation

• Key customer concentration

• Financial swings before listing

AI brings all those signals to the surface instantly.

The goal of this tool is not to replace judgment, but to speed up clarity.

A process that usually takes analysts 2–3 days can now be compressed to ten minutes.

How It Works

Reads the company’s DRHP via Perplexity.

Extracts all financials, management disclosures, and risk sections.

Breaks them into structured tabs.

Highlights inconsistencies and pattern shifts.

Builds a complete dashboard ready for analysis.

No manual reading required.

No downloading PDFs.

No searching for data.

Just structured interpretation.

Example Dashboard Output

You’ll find the complete boAt dashboard inside this edition.

It includes:

• Revenue, EBITDA, PAT trends

• Leverage profile

• Promoter exits

• Segment-level trends

• Valuation comparison

• Key risks

• Industry view

• Post-IPO shareholding

Everything is automatically generated from the DRHP.

Click to View: Dashboard Output

How to Read DRHP Data

The dashboard highlights signals across four blocks:

1. Promoter and Management

2. Look for exits, ownership drops, sudden structural changes.

3. Financial Pattern Shifts

4. Negative CAGRs, sudden profitability improvements, margin reversals.

5. Concentration and Dependencies

6. Customer, geography, vendor, segment reliance.

7. Key Risks

8. Read the risk section carefully. It often reveals what management will never say publicly.

Quick rule:

If promoter behavior and financial trend diverge, look deeper.

Who It’s For

Anyone who analyses IPOs:

• Equity analysts

• Investment advisors

• PMs

• Traders

• Students preparing for research roles

• Founders studying market signals

• Retail investors who want more than social-media opinions

Framework Used

DRHP Forensic Framework

• Reads promoter history

• Identifies financial shifts

• Maps segment-level weakness

• Extracts legal and regulatory disclosures

• Highlights operational anomalies

• Compares peer valuation

• Scores disclosure clarity

This is typically how institutional analysts read a DRHP, now automated.

Access the Toolkit

Simply copy the prompt, paste it into your Perplexity Labs workspace, enter the IPO name, and run it.

Execution time: 8–10 minutes for a complete IPO dashboard.

Prompt

🖥️ **INTERACTIVE DASHBOARD PROMPT — DRHP-BASED IPO ANALYSIS (INDIA EDITION)**  
© Shikshan Nivesh Research | All Rights Reserved

---

### ASSET TYPE
Create an **interactive Bloomberg-style dashboard** (not a static report).  
Output should render as a **multi-tab analytical interface**, not plain text.  
Each tab must include:
- Interactive tables  
- Dynamic charts (1600 × 1000 px, 300 DPI)  
- Concise factual commentary blocks  
- Dark Bloomberg theme with green (positive) and red (negative) highlights  

---

### ASSET NAME
“IPO Financial & Strategic Dashboard — <Company Name> ( DRHP Based )”  
**Credit:** Research & Insights by Shikshan Nivesh Research  

---

### TAB STRUCTURE  
Create **12 interactive tabs** in the sequence below.  
Each tab = data table + commentary + chart panel.  

---

#### 🟩 TAB 1 — Executive Summary
• Overview of <Company Name>’s business model, IPO rationale & market opportunity.  
• Show issue size (₹ crore), Fresh Issue vs OFS split.  
• Highlight strengths and investor concerns.  
• Chart 1 — IPO Structure (Fresh Issue vs OFS).  
• Footer Credit: Source – Company DRHP | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 2 — Business Overview
• Table: Key business segments and revenue % (FY23–FY25).  
• Explain products, geographies, customers.  
• Chart 2 — Business Model / Value Chain Map.  
• Footer Credit: Source – Company DRHP | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 3 — Industry Landscape
• Table: Industry size (₹ crore), CAGR, key competitors, market share.  
• Comment on demand drivers & regulations.  
• Chart 3 — Industry Growth vs Company CAGR.  
• Footer Credit: Source – Company DRHP | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 4 — Financial Performance
| Metric | FY23 | FY24 | FY25 | CAGR |
| Revenue (₹ cr) |  |  |  |  |
| EBITDA (₹ cr) |  |  |  |  |
| EBITDA Margin (%) |  |  |  |  |
| PAT (₹ cr) |  |  |  |  |
| Net Margin (%) |  |  |  |  |

• Chart 4 — Revenue / EBITDA / PAT Trend.  
• Footer Credit: Source – Company DRHP | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 5 — Balance Sheet & Leverage
| Metric | FY23 | FY24 | FY25 |
| Total Assets (₹ cr) |  |  |  |
| Net Worth (₹ cr) |  |  |  |
| Total Debt (₹ cr) |  |  |  |
| Debt/Equity (x) |  |  |  |

• Chart 5 — Debt/Equity Trend & Post-IPO Effect.  
• Footer Credit: Source – Company DRHP | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 6 — Cash Flow Profile
• Table: OCF, CapEx, FCF (FY23–FY25).  
• Chart 6 — OCF vs PAT.  
• Footer Credit: Source – Company DRHP | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 7 — IPO Offer & Use of Proceeds
| Particulars | ₹ crore | % of Issue |
| Fresh Issue |  |  |
| Offer for Sale |  |  |
| Total Issue Size |  |  |

• Chart 7 — Use of Proceeds (Pie).  
• Footer Credit: Source – Company DRHP | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 8 — Promoter & Management
• Table: Promoters & key executives with shareholding %.  
• Chart 8 — Pre vs Post IPO Shareholding.  
• Footer Credit: Source – Company DRHP | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 9 — Peer Comparison & Valuation
| Company | FY25 Revenue | EBITDA Margin | PAT Margin | P/E | EV/EBITDA | ROE (%) |
| Peer 1 |  |  |  |  |  |  |
| Peer 2 |  |  |  |  |  |  |
| <Company Name> |  |  |  |  |  |  |

• Chart 9 — Relative Valuation (Scatter Plot).  
• Footer Credit: Source – Company DRHP | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 10 — Key Risks & Red Flags
• Table & Chart 10 — Risk Heat Map (High/Medium/Low).  
• Footer Credit: Source – Company DRHP | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 11 — Analyst & Media Commentary
• Table: Public analyst and media insights.  
• Chart 11 — Sentiment Distribution Bar.  
• Footer Credit: Source – Public Media Reports | Credit – Shikshan Nivesh Research  

---

#### 🟩 TAB 12 — Overall Assessment
• Rating Scale (1–5, 0.5 steps).  
• Chart 12 — Overall Rating Gauge.  
• Footer Credit: Compiled by Shikshan Nivesh Research  

---

### DASHBOARD SETTINGS
• Theme: Dark (#101010) background, #EDEDED text.  
• Highlights: #00B050 (green), #FF4D4D (red).  
• Font Family: “Inter”, fallback “Roboto”.  
 – Headlines 18–20 pt SemiBold  
 – Tables 14–15 pt Medium  
 – Numbers 15 pt Roboto Mono  
 – Commentary 14 pt Regular (line-height 1.5)  
• Layout: Left panel (tables) / Right panel (charts).  
• Top tab navigation fixed.  

---

### RULES
• Use only DRHP and SEBI data — no forecasts or speculation.  
• Round financials to ₹ crore (one decimal).  
• Keep tone neutral and fact-based.  

---

### DISCLAIMER TAB (Auto-Generated)
“This dashboard is prepared from publicly available DRHP filings and SEBI disclosures for <Company Name>.  
It is produced for educational and analytical purposes only and does not constitute investment advice.  
Research and Visual Framework by Shikshan Nivesh Research.”  

---

### END OF PROMPT

In Summary

The DRHP-Based IPO Dashboard makes IPO analysis fast, transparent, and structured.

It reads the prospectus, extracts insights, and visualises everything in minutes.

IPO research now begins with DRHP + AI.

Bonus Tool: Try the SuperAnalyst Command Centre (Basic)Free

If you’d like to take this even further, you can now access my SuperAnalyst Command Centre, Basic Version absolutely free.

It’s a conference call analyzer built for analysts, students, and investors who want to:

• Decode management tone and intent in minutes

• Run prompt templates for quarterly results & management commentary

• Generate AI-based summaries with sentiment and guidance signals

• Standardize how you analyze calls across multiple sectors

You don’t need to build anything, it’s ready to use.

👉 Access here: SuperAnalyst Command Centre (Basic Version)

(Includes all core prompts and AI templates I personally use during every results season.)

🤝 Help Us Grow This Circle

Thank you for reading and supporting Alpha with AI. If you share this edition with even one person who might find it valuable, it means the world to us and helps this project reach those who need it most.

You use Gmail? Do this:

If you use Gmail, you might never receive my emails in your inbox. But you can fix this in 10 seconds:

1. Reply to this email with “hello!”.

2. Move this email to your Primary folder like this:

📩 What’s Next

You’ll now receive one new AI-based finance or research workflow every week, covering topics like research automation, portfolio decoding, valuation models, and data visualization.

If you’d prefer not to get these updates, you can unsubscribe.

Otherwise, welcome aboard, this is the next edition of Alpha with AI.

At Shikshan Nivesh, our goal is simple, to make financial research faster, smarter, and more accessible.

Because the future of analysis isn’t about who knows Excel best.

It’s about who builds thinking systems that scale.

Written by Shubham Borkar | Research & Insights by Shikshan Nivesh AI Team

Financial Clarity. Insightful Ideas.

Disclaimer

This Guide & Prompt Kit and its outputs are for educational and research purposes only. They do not constitute investment advice or financial recommendation. Always verify disclosures and consult qualified professionals before making investment or business decisions.

Links & Follow

Thank you for being part of the Shikshan Nivesh community.

• ▶️ For video explainers on AI, finance, and smart investing, subscribe to our YouTube channel Alpha with AI

• 💬 Join our WhatsApp community for regular updates on finance, AI, and smart investing tools.