A year ago, I wrote one post on Substack and then disappeared.

I didn’t get it. I published once, watched nothing happen, and walked away. For months the account just sat there, dead. I’d convinced myself Substack wasn’t for someone like me, a finance guy writing about AI research workflows, not exactly the usual Substack fare.

Then around August last year, I started doing something different. I stopped trying to publish and just started reading. And slowly it clicked, what Substack actually was, and what it could be if I took it seriously.

On 21 November, I wrote my first real newsletter under Alpha with AI, the publishing arm of Shikshan Nivesh, my AI consultancy for finance professionals. Practical, no-bullshit workflows for analysts and investors. Many of them pulled straight from real client work. By February I was writing notes too, finding the rhythm. And somewhere in the last three months, it stopped feeling like an experiment.

Why now

Here’s the thing I didn’t fully expect.

What started as a giveaway turned into something I take seriously. Over the last three months especially, the workflows have gotten sharper, more practical, pulled from actual problems I’m solving in client work. And they take real time to build properly. A single workflow worth publishing is hours of testing, refining, and writing, not a quick post.

For over six months, all of it has been free. Every workflow, every framework, every prompt. I don’t regret that for a second, it’s what built this, and it’s what got us close to 5,000 readers.

But I’ve reached a point where I can see what this could be if I gave it everything. Two, three times the depth. Better, more rigorous work. And to do that properly, it needs to be supported.

So as we approach 5,000 readers, I’m making Alpha with AI a premium newsletter. Not to put up a wall, but to build something better behind it.

What you get

If you become a member, here’s what opens up.

First, the archive. Six months of workflows, frameworks, and prompts, the entire library, in one place. Insider trade analysis, capital rotation diagnostics, the Claude Code research stack, the Obsidian layer that ties it together. Everything I’ve published, ready to read the moment you’re in.

Second, everything new. Every workflow I publish going forward lands in your inbox, the full version, no paywall cutting it short. And going premium is exactly what lets me make those deeper and more rigorous than what came before.

There’s also a second door. The Alpha with AI Club on our website is a fuller membership: it includes the newsletter and archive, plus exclusive extras, future masterclass access, downloadable workflow and skill files, and the community itself. If you want the whole ecosystem and not just the reading, that’s the one. For pure reading, though, Substack stays the cleanest experience.

This was always built for one kind of person: the analyst or investor who wants to actually work with AI, not just read about it. If that’s you, the whole thing is now yours to use.

The launch offer

Claim 25% off →

Here’s the part for anyone who’s been reading and wants in.

For the next two weeks, until 8 June, you can join at 25% off your first year. It’s my way of thanking the people who showed up early, before there was ever a paywall.

Prices show in your own local currency automatically, so you’ll see a familiar number at checkout. As a rough guide, membership works out to around $39 a month or $345 a year, with the launch discount bringing the first year down to about $260.

If you’ve found these workflows useful, this is the moment. The offer closes on 8 June, and after that it’s full price.

Claim 25% off →

Thank you, genuinely

I started this a year ago not knowing if anyone would read it. Now we’re almost at 5,000.

Whatever you decide, paid or free, I’m grateful you’re here. The free editions and the notes aren’t going anywhere, and I’ll keep showing up either way. Going premium just lets me make the work better for the people who want to go deeper.

If you’ve gotten something out of these workflows, the simplest way to support what comes next is to share them. Forward this to one person who’d find it useful, or pass along a post that helped you. That’s how this got to 5,000 in the first place.

More soon. The best work is still ahead.

- Shubham

🧰 Free and Premium Resources from Shikshan Nivesh

If you want the frameworks, prompts, and workflows I use across my research stack, free and paid, they alternatively also live on my website: shikshannivesh.com. The industry research playbook, the $100K Research Framework, the Kill Report prompt, and more. Everything built for analysts and investors who’d rather spend their time thinking than clicking.

🤝 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.

Claim 25% off →

Ninety days ago, I opened a terminal for the first time and typed claude. Today, the same stack runs my entire investment research workflow. Screening, scraping, modeling, drafting, monitoring. The terminal stopped being intimidating somewhere around day three.

Three newsletters in, you’ve seen most of the moving parts. Part 1 was the confession, why a finance guy would even open a terminal in the first place. Part 2 was the full setup: Claude Code, Cursor, Obsidian, Playwright, Firecrawl. Part 3 was the first real workflow, decoding insider trades.

If you’re new here, those three are worth reading before this one. They build the system. This newsletter is about the part of that system most readers underestimate, and the part doing the most quiet work in the background.

Obsidian.

1. The Bottleneck Was Never the AI

Picture a Monday morning. You’re scrolling X with your coffee. Someone shares a rese…

Read more

This is an experiment.

Alpha with AI has always been a writing-first newsletter. That is not changing. But this week I wanted to try something different, a video podcast format, where the workflow comes alive on screen rather than on the page.

If you like it, I’ll do more of these alongside the written pieces. If you prefer the written format, that is coming back soon.

Either way, would love to know what you think in the comments.

This is Part 3 of the Claude Code series.

If you are new here, Part 1 was about why Claude Code is not just a coding tool. Part 2 was the full investment research setup: Obsidian, Playwright, Firecrawl, the whole stack.

This one is where the actual research begins.

Insider trade data is one of those signals everyone has an opinion on.

Half the community ignores it entirely. The other half treats every transaction like a gospel signal.

Peter Lynch settled this a long time ago — insiders sell for hundreds of reasons, but they buy for on…

Read more

If you’re a finance person, you’ve probably looked at Claude Code once and looked away.

A black terminal. Commands that mean nothing. Something for engineers, not for someone who spends their day in spreadsheets and annual reports.

Claim 25% off →

That was my reaction too.

I’ve now been running my entire investment research workflow on Claude Code for sixty days. Screening, scraping, modeling, drafting reports, monitoring portfolios. The terminal stopped being intimidating somewhere around day three. By day ten, I had stopped opening Claude for research entirely.

Here’s what nobody told me, and what I want to tell you: Claude Code is for coding if you want to code. It’s for cooking if you want to cook. It’s for shopping if you want to shop. And if you’re really into finance, Claude Code is for finance too.

The “code” in the name is the most misleading part of the product.

This newsletter is the setup guide I wish …

Read more

I have watched the Big Cycle video eleven times.

Every time goes the same way. I open YouTube. I tell myself this is the watch where I take real notes, build a real framework, integrate it into my actual research. I scribble for the first ten minutes. I nod at the part about debt cycles. I get up for something in the kitchen. I come back. The video is still playing and Dalio is still talking about empires.

Claim 25% off →

By the end I have three pages of notes I will never look at again, a vague sense that I understand the Big Cycle better, and a stock screener still open in another tab waiting for me to come back to the actual work.

It is not just the video. There is a shelf next to my desk. On it sits Principles, Big Debt Crises, Changing World Order, The Intelligent Investor, Built to Last. Books I bought because every serious investor I respect said I should read them. Books I have opened, dog-eared, start…

Read more

I gave up on Claude Code twenty times.

Maybe more. I lost count somewhere around attempt fifteen.

Every time went the same way. I’d read a tweet about someone doing something incredible with it, feel the fear of missing out kick in, open a terminal window on my Mac, type a few commands I barely understood, get a cryptic error, close the terminal, and tell myself the same lie: “I’m a finance guy. This isn’t for me. I’ll stick with the chat window.”

Then last month, something broke that pattern.

Not because Claude Code got easier. It didn’t. The terminal still looks exactly as scary as it did two years ago.

What changed was the reason to stay.

I found a way to give Claude Code a brain, a real, grounded, zero-hallucination research brain. Every annual report I own. Every earnings transcript I’ve downloaded. Every consultancy PDF sitting in my Downloads folder. All of it, indexed, cited, queryable, fro…

Read more

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, update…

Read more

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…

Read more

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 t…

Read more

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 …

Read more

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: Jo…

Read more

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 fro…

Read more

“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 bu…

Read more

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 …

Read more

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.

…

Read more

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 v…

Read more

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…

Read more

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:

Read more

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:’

Read more

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 …

Read more