In February I wrote that the traditional IT middleman was dead.

I meant it. That edition argued AI was collapsing the cost of building software to almost nothing, and that the people who bill by the hour to build it for you were standing exactly where the flood would hit first. Within a week the market agreed, loudly, and billable-hour businesses everywhere repriced. (If you missed it, the argument lives here: the traditional IT middleman is dead.)

Then, on the 22nd of June, I placed a buy order for the biggest billable-hours firm on the planet.

Accenture. Nearly eight hundred thousand people. The firm that boards call when they want change made without their own fingerprints on it. The stock had been cut in half in twelve months while everything else with AI in the story made new highs, and somewhere in that gap I stopped seeing an AI casualty and started seeing a mispricing.

Now, I usually never buy a position in one go. I accumulate. Small orders, spaced out, so the market has time to prove me wrong before I am fully in. What I placed that morning was the first of those small orders. A toe in the water, nothing more.

Here is the confession this edition is built on.

While preparing this deep dive, I opened my account to check my cost basis. There was no cost basis to check. The order never went through, and I had spent two weeks believing my accumulation had started when it had not. The stock is up around ten percent since. That stings more than a loss would. A loss at least means you acted.

So I am not writing this to defend a position. I do not have one. I am writing it to decide, with the filings open and you watching, whether that first order deserves to be placed again. And I do not get to shrug my way to an answer. Both of my bets are already on the table. I wrote the bear case in February. I placed the bull order in June. One of those two people was wrong, and this edition finds out which one.

Before we open a single filing, you should know something about this company. The market has sentenced Accenture to death twice before.

The first sentence came from its own family. Accenture began as the consulting arm of Arthur Andersen, the accounting giant, and by the late nineties the consultants were the ones making the money, handing up to fifteen percent of their profits to the parent nearly every year. They wanted out. The divorce took years of arbitration, and in August 2000 the ruling came down. The parent had demanded roughly fourteen and a half billion dollars. The arbitrator awarded it no damages at all. Just the roughly one billion dollars of profit-sharing money it was owed anyway, half of it already sitting in escrow, and one condition: surrender the Andersen name entirely, and go. An employee in the firm’s Oslo office named Kim Petersen won the internal naming contest with a made-up word, accent on the future, and in January 2001 Andersen Consulting became Accenture.

Within a year, the name it had been forced to surrender was radioactive. Arthur Andersen was Enron’s auditor, and it did not survive the scandal. Almost a century of reputation, gone. The orphan that paid a billion dollars to lose its family name had bought, by pure accident, the cheapest insurance in corporate history. It listed at $14.50 a share in July 2001 and spent the next two decades compounding into the largest technology consultancy on earth.

The second death sentence came a decade ago, and it will sound familiar. Cloud software was going to make integrators obsolete. Why pay consultants by the hour when the solution arrives turn-key, out of the box? You know how that ended. In the decade that followed, revenue more than doubled.

Now the third sentence has been handed down, and this time the executioner is supposed to be AI. AI writes the code, drafts the deck, does the work. Who needs eight hundred thousand consultants? The market believes AI is the largest business transformation of our lifetime, and it also believes the firm hired to run that transformation is dying of it. Both of those cannot be fully true at the same time.

Maybe the third sentence is the one that sticks. Companies do not get infinite lives, and sometimes the scare everyone laughed off twice is real the third time. That is exactly what this deep dive exists to find out.

I pointed Claude Code at every annual report, quarterly filing and earnings release Accenture has put on EDGAR since 2023. Eleven documents, every number pulled straight from the source, and one standing instruction: build the case against me.

(The whole rig, Claude Code running inside Obsidian with every filing it pulls saved into the vault, is its own edition: how I set up Claude Code as my investment research analyst, and the 2.0 rebuild that moved everything inside Obsidian. Start there if you want to run this yourself.)

What came back is stranger than the bull story or the bear story. There is a number Accenture spent two fiscal years leading its earnings releases with, and this year it quietly stopped appearing.

Hold that. We will get to it.

THE 60-SECOND THESIS

What they do. The world’s largest technology consultancy. 799,000 people, split almost exactly in half between designing large corporate transformations (consulting) and running the systems those transformations produce (managed services), on $69.7 billion of FY2025 revenue. Almost none of it needs capital: $600 million of capex against $10.9 billion of free cash flow last year. The asset is people billed by the hour. Which is exactly what the market has turned against.

Why it is down. The market has repriced Accenture as an AI casualty, and the dents are real, not imagined. Local-currency growth slowed 5, then 4, then 3 percent through FY2026. The US federal business, 8 percent of revenue, is being cut under DOGE (the US government cost-cutting department) and costs about a point of growth. Managed services bookings (new contracts signed, the order book), the bigger half of the business, fell 16 percent last quarter. Even the filing language has cooled: pricing went from “improved in several areas” to “relatively stable”.

Why I think that is the mispricing. Cut in half in a year, Accenture now trades at a free cash flow yield near 13 percent on management’s own $10.8 to 11.5 billion guide, by my math. The company is priced for decay and guiding for growth. One of those two is wrong. My view, and the reason for that June order: in the near term, everyone wants AI and almost nobody can implement it. Accenture has logged 104 quarterly client bookings of $100 million or more so far this year, up 13 percent, and its filings say clients keep prioritizing large-scale transformations to become AI-ready. Structurally, I believe companies hire Accenture for reasons AI does not remove: cover for hard decisions, someone else to blame, and speed they do not have in-house. That is an opinion, not a fact. The rest of this piece exists to test it.

What could turn it. The federal drag stops being news, since the guide already implies 4 to 5 percent growth without it. Capital returns the price ignores: a buyback raised to $7.5 billion, a dividend up 10 percent, $5 billion of net cash still on the books. And AI bookings visibly converting into revenue. Whether AI replaces the billable hour faster than it deflates it is the question that decides everything, and there is one number, quietly missing from the last two earnings releases, that sits at the center of it. Both get their full sections below.

THE BUSINESS IN ONE LENS

Most coverage treats Accenture as one giant consulting firm. The filings describe something more interesting: two different businesses wearing one badge, and AI is hitting them in opposite ways.

The first business is consulting. Senior people who design large transformations, project by project. That was $35.1 billion of revenue last year, growing 5 percent in local currency. The second business is managed services: multi-year contracts to run the systems and operations those transformations leave behind. That was $34.6 billion, growing 9 percent. And in the first nine months of this fiscal year, the second business became the bigger one for the first time, $27.9 billion against $27.6 billion. I had Claude Code pull the revenue tables from the last three 10-Qs and reconcile the two halves quarter by quarter, and that crossover is the quietest important fact in the filings.

Why it matters: consulting is where an AI wave shows up first as demand. Someone has to design the transformation, pick the models, rewire the workflows. Managed services is where AI shows up as deflation. It is the running of systems, the processing of invoices and claims and tickets, the recurring human hours that agents are supposed to replace. Same company, opposite exposure. You are not buying one bet on AI. You are buying both sides of it, in one stock.

And in the latest quarter, the two halves diverged exactly along that line. Consulting bookings rose 11 percent in local currency. Managed services bookings fell 16. One honest caveat before anyone extrapolates a single quarter: bookings are lumpy, and a handful of mega-deals moving by a few weeks can swing that number. But the direction matches the exact fear the market is pricing, and it is the line I will be watching hardest from here.

Step back and the machine itself looks nothing like a company in decline.

Margins tell the honest version: operating margin was 14.7 percent last year on a GAAP basis, 15.6 adjusted, and gross margin actually slipped to 31.9 percent, which the 10-K attributes to higher payroll costs. This is not a business getting more profitable per hour. It is a business getting bigger while paying more for its people. Hold that tension; it comes back in the hinge.

Geographically, the Americas are half the company, EMEA about a third, and Asia Pacific, the smallest slice, is suddenly the fastest growing at 9 percent. The balance sheet fits in one line: $10.2 billion of cash against $5.1 billion of debt, the first term debt in the company’s history, which is its own story for later. (Reading what sits above the equity holder is a discipline with its own edition: the whole debt structure from one filing.)

This is the machine the Andersen orphan built: capital-light, cash-gushing, buying a handful of small firms every year as its R&D department, and handing everything left over back to shareholders. The question this piece exists to answer is not whether the machine works. It is whether AI changes what the machine gets paid for.

WHY IT’S DOWN

The company admits the bear case in writing

I did not find the strongest version of the bear case in a short report or on a podcast. I found it in Accenture’s own annual report. I had Claude Code read the FY2025 10-K’s risk factors and pull every sentence about AI, and this one deserves to be read slowly:

“Some services and tasks currently performed by our people have been and will continue to be replaced by automation, including AI-enabled solutions, which will lead to reduced demand for our services and/or adversely affect the utilisation rate of our professionals, if demand for those services is not replaced by demand for new solutions and services... If we are unable to introduce or if our clients do not accept new pricing or commercial models that reflect the value of these AI-enabled solutions, our results of operations may be adversely affected.”

Not “may be replaced.” Will, unless new demand replaces what automation takes. The company that sells the AI transition has told its own shareholders, in a filed document, that AI shrinks the thing it currently bills for, and that survival means selling something new in its place. The whole stock is a bet on that unless. Everything else in this section is that sentence showing up in the numbers.

The growth is slower than the headline

Reported revenue grew 6, 8, and 6 percent across the three quarters of FY2026. Strip out currency and it is 5, then 4, then 3. The dollar did the flattering: foreign exchange added as much as 4.4 points in a single quarter. Management’s own full-year guide has narrowed from 2 to 5 percent in local currency to 3 to 4, with the top end doing the falling.

Washington took a bite

Accenture Federal Services was 8 percent of revenue last year, and roughly a third of the Health and Public Service group. Under DOGE, the filings describe procurement delays, price reductions, contract scope cuts, and outright terminations, with the GSA instructing every federal agency to review its consulting contracts. The result: a segment that grew 6 percent last year is shrinking this year, and management pegs the drag at about one point of total company growth, roughly $700 million by my math. There is also an open Department of Justice matter at the federal unit; it belongs in the risk section, and I will come back to it there.

Share

The order book cooled exactly where it hurts

Full-year bookings actually fell 1 percent in FY2025. This year started strong, then Q3 brought the number that matters: total bookings down 3 percent in local currency, and managed services bookings, the bigger half of the business, down 16. And the filings’ language about pricing has been quietly walking backwards. I had Claude Code line up the same sentence in the MD&A (the management commentary section of a filing) across four consecutive filings: “improved in several areas” became “improved in some areas” became “relatively stable.” That is how pricing pressure sounds when a company is choosing its words carefully.

The margin is being defended, not expanding

Gross margin fell 70 basis points last year to 31.9 percent, the payroll squeeze from the last section. The operating margin held up, but look at how: a $923 million severance and “business optimization” program that cut roughly 22,000 people from the February 2025 peak, though hiring has since resumed, and utilization (the share of employee time billed to clients) pushed to 93 percent, the highest level anywhere in these filings. The 10-K itself warns that utilization run too high damages engagement and drives attrition. Squeezing harder is a strategy with a ceiling.

And the challengers are smaller, faster, and sometimes your own client

The 10-K names the competition plainly: clients and ecosystem partners building their own AI capability, and “new AI-native companies.” The structural fear is simple. If AI collapses the cost of delivering technology work, the advantage of an 800,000-person pyramid built on billable hours inverts. Every mid-size AI-native shop is pitching exactly that story to Accenture’s clients right now.

Add it up and this is not a stock that fell on a misunderstanding. The bear case is coherent, filed, and partly visible in the numbers already. The market looked at all of it and cut the price in half.

The only question that matters is whether it stopped at the right floor. That question has one hinge, and the company’s own disclosures, including one number that quietly disappeared, are where we go next.

This is where the paid section begins. The free half gave you the setup, the history, and the honest bear case. The paid half takes the hinge apart, shows the number that vanished, and lands on what I am doing with that June order.

Read more

A better model shipped this month. Another one ships next month. You know the ritual. The timeline lights up, the benchmark charts fly, and somewhere in the back of your head a quiet worry starts. Is my whole setup obsolete again?

I want to offer you a different way to think about that worry, and it is one you already own. You are an investor. So put your setup on a balance sheet.

Every asset you have ever analysed sits in one of two buckets. Some assets depreciate. The computer you are reading this on lost value the day you bought it, and it has lost a little more every day since. And some assets compound. They grow the longer you hold them, quietly, and the growth feeds on itself.

Now look at where your attention goes when that worry starts. It goes to the model. And the model sits squarely in the first bucket. Whatever frontier model you run today will be mid-tier in six months, not because it got worse, but because something better always ships. That is fine. That is the one part of your stack you should want to be replaceable.

Here is the uncomfortable part. The second bucket, the compounding one, is where your actual edge lives. And for most researchers, it sits empty. Think about everything you have read this year. Every filing you pulled apart, every sharp thread you saved, every note you wrote on a company and swore you would come back to. Where is all of it right now? If you are honest, it evaporated. Scattered across bookmarks, chat histories, and folders you will never open again.

That is the real bottleneck, and it has nothing to do with which model is winning this month. The one asset in your research life that could compound is the one leaking value every single day, while all your attention goes to the part that was always going to be replaced.

The model is replaceable. The memory is not.

Most people have this allocation exactly backwards. All their attention goes to the depreciating asset, and the compounding one sits unbuilt.

For the last 120 days I have been building the compounding side, and this edition is the complete setup, start to finish. If you are new here, you do not need to read anything else first. Everything you need is on this page.

Some of you built the first version of this system with me, from How I Set Up Claude Code as My Investment Research Analyst. That piece is free, it is one of the most read things I have published, and most of it still holds. The installation steps, the walkthrough video, the foundations. But the setup did not stand still. I ran it every single day for four months, and it evolved. One tool got fired from the stack entirely. And a plain folder of text files quietly became the most valuable asset I own as a research operation.

Two months in, I want to know something, because this edition reads differently depending on your answer.

Whichever you picked, you're covered. If you built it, this is what yours grows into. If you dropped off or never started, this edition is the simpler second chance, and you'll see why in two sections.

The Claude Code + Obsidian Setup for Investment Research, From Zero

Let me build the whole thing in front of you, assuming you are starting from nothing.

The system runs on two tools. Both are free to install.

Claude Code is the analyst. It lives in a terminal, which sounds intimidating and stops being intimidating by day three. You talk to it in plain English. Tell it to pull a filing, read a transcript, screen for something specific, write a memo, and it goes and does the work on your computer, in your files, and shows you everything it did. If a terminal is a dealbreaker for you, hold that thought, because this edition removes that problem in a way that was not possible when I started.

Obsidian is the memory. It is a free app that points at an ordinary folder on your computer, and every note you create inside it is saved as a markdown file. Markdown, the .md format, is just plain text with simple symbols for structure, a # for a heading, a dash for a list. Humans can read it raw. And it happens to be the format AI models read most easily and most reliably, which is why almost every AI tool speaks it natively. So a folder of markdown files is, by accident of design, the most AI-ready research library that exists. No database, no export, no API. Obsidian’s only job is to make that folder pleasant to live in. (Obsidian setup guide)

Installing both takes about ten minutes. Obsidian is a normal app. Download it from obsidian.md, open it, and create a vault, which is nothing more than choosing a folder on your computer and giving it a name.

Claude Code installs with one command, and you should take that command from the source, because it stays current there. Open the official Claude Code quickstart at code.claude.com/docs/en/quickstart. You will see two install commands. On a Mac, copy the Terminal one and paste it into Terminal. On Windows, copy the PowerShell one and paste it into PowerShell. Press enter, wait a minute. Then type claude, press enter, and sign in with your Claude subscription. The analyst is installed. (Claude code setup guide)

And here is the standing rule for this entire edition. If any step confuses you, at any point, copy the confusing part, paste it into Claude, and ask it to walk you through it. You are setting up an AI analyst. Let it do its own tech support. This one habit is the difference between the people who finish setups like this and the people who quit at the first error message.

Analyst plus memory. That is the entire idea. Everything you read gets captured into the folder as markdown. Everything the analyst produces gets filed into the folder as markdown. Ask a question next month, next quarter, next year, and the analyst answers with everything the folder has ever collected behind it.

One more thing about this architecture, because it is the reason this edition will still make sense long after the current model leaderboard is forgotten. Nothing in this setup is married to Claude. Claude Code is the analyst I hire, but the chair itself is open. OpenAI ships Codex. xAI just shipped Grok Build. Moonshot has Kimi Code, MiniMax slots in too, and every serious lab now has a terminal agent of its own. Any one of them can sit in this same chair, pointed at this same vault, reading the same memory. The setup does not care whose model is winning the month.

That is why I will make a claim I almost never make about anything in AI. This setup will still be relevant six months from now, a year from now, probably two. And in this industry a year is like five anywhere else. It survives for one reason, and it is the whole argument of this edition: everything durable here lives in the folder, not in the model.

If you built the original version with me, you know there used to be a third tool sitting between these two. Cursor, the code editor I used as the workspace where the analyst and the memory met.

But run a system every day for four months and it tells you what it actually needs. Mine told me something I did not expect.

It did not need the middleman.

I Removed Cursor: Now the Entire Research Stack Lives Inside Obsidian

The middleman was doing two jobs.

Cursor gave me a terminal to run Claude Code in, and an editor to open my vault files in. That was it. Two windows in one app. And for months I treated that arrangement as the cost of doing business, until I watched what my hands were actually doing all day. Write in Obsidian. Switch to Cursor to run the analyst. Switch back to Obsidian to read what it produced. Switch to the browser to read something new. Clip it. Switch back. My research lived in one place and my attention lived in four.

Then I found out Obsidian could do both of Cursor’s jobs itself.

The first job, the terminal, is one community plugin. It is called Terminal, install it and a full terminal opens inside Obsidian, right next to your notes. In Obsidian, community plugins are built by users and installed from inside the app: Settings, then Community plugins, then Browse, and search for it by name.

Core plugins, which you will meet in a minute, are different, those are Obsidian's own, already built in, you just switch them on from Settings, then Core plugins. Install Terminal, open it next to your notes, type claude, and the analyst is now sitting inside the memory. Not next to it. Inside it. And notice what that plugin actually gives you: a terminal, not a Claude terminal. The day you want to run a different model’s CLI in there, Codex, Kimi, whatever ships next, it is the same plugin. Hold that thought, because it is the whole final section of this edition.

The second job, editing and reading the files, Obsidian was always better at. That is literally what it is for.

So Cursor left the stack. Not because it is a bad tool. Because the system stopped needing it, and every tool the system stops needing is one less thing a model upgrade can break.

And if the terminal itself is the thing that has kept you away from this entire setup, this is where I get to keep a promise from earlier. There is a plugin called Claudian. It puts Claude inside Obsidian as a chat window. No terminal, no black screen, no blinking cursor. You talk to it the way you talk to any chat, except it is sitting inside your vault, reading and writing your actual research files. The people who quit this setup at the terminal stage now have a door that does not require one.

Before I close the last window, meet the intake of the entire system: Obsidian Web Clipper. It is a free browser extension built by the Obsidian team, and it does one thing. Any page you are reading, an article, a filing, a thread worth keeping, one click, and it lands in your vault as a markdown file. In its settings you choose where clips land. Mine all go to one folder called raw, the system’s inbox, and that folder is about to matter in the next section. This is the moment reading stops being something that evaporates and starts being something you keep.

One more plugin closed the last window I was switching to. Web Viewer, and this one is not even a community plugin, it ships inside Obsidian. Turn it on and external links open inside Obsidian instead of your browser. Read the article there. Clip it from there with Web Clipper, and with Local Images Plus installed, every chart and image in the article downloads into the vault alongside the text, so the clip stays whole even if the page dies next year. Reading, clipping, filing, analyzing, writing. One window.

Two small quality-of-life touches before we move on. A plugin called Iconize lets you put icons on your folders, which sounds cosmetic and is, but a vault you enjoy looking at is a vault you actually use.

The second one I have never shown in writing before. At the bottom of my terminal sits a small status line: the folder Claude Code is working in, the model it is running with its context size, and a little rectangular bar showing how much of that context is already used, shifting from green to orange to red as it fills. One glance tells me where I am, what is running, and how much room is left before the model starts forgetting.

You do not write any code to get this. Claude Code has a /statusline command, and you describe what you want in plain English, the way you would describe it to a colleague. Mine was essentially: show me the current folder, the model name with its context size, and a small percentage bar for context usage that changes color as it fills up. Claude Code builds its own status line. It is a thirty-second setup, and it is the single thing visitors ask about first when they see my screen.

One last setting, and the screenshots have already given it away. At the bottom of my terminal it says bypass permissions on.

By default, Claude Code works like an advisory account. Before every single action, reading a file, writing a note, running a search, it stops and asks you first. Safe, but for real research it breaks the flow completely. You give it one task and then spend ten minutes clicking yes, yes, yes.

Bypass permissions turns the relationship discretionary. You give the mandate once, and it executes the whole workflow without stopping to ask. The community calls this YOLO mode, but discretionary is the honest word for what it is. Press shift and tab inside Claude Code to cycle between the modes, and the status line shows you which one is active.

One rule comes with the mandate, the same one that comes with any discretionary account: be careful what you hand over. A model with full permissions can edit and delete files. Point it at your research vault, never at your entire computer. The vault is its sandbox. Everything it needs lives there, and everything it can touch ends there.

That is the whole migration. Cursor out, one terminal and one browser in, both living inside Obsidian, and the count of windows I touch in a research day went from four to one.

But plugins are furniture. An empty vault with good furniture is still empty. Before this system can research anything, it needs a structure for information to flow through, and a brain that tells the analyst how to behave inside it. On day one, that is three folders and three small files.

CLAUDE.md: The One File That Makes Any AI Model Research Like You

Start with the structure. Open the terminal inside Obsidian, start Claude Code, and paste this:

Create this folder structure for my knowledge base:

- raw/ — this is my inbox where I'll dump source material
- wiki/ — this is your domain, you'll write and maintain everything here
  - Create a _master-index.md inside wiki/ with the heading "Knowledge Base Index"
    and a note that says "Topics will be listed here as they are created."
- output/ — this is where query results and reports go

Just create the folders and that one file. Nothing else yet.

Ten seconds later, three folders sit in your sidebar. raw is the inbox, everything you want the system to learn from gets dumped there. wiki is the library the analyst builds and maintains out of it. output is where finished work lands. That is the entire flow of information: in through raw, organized into wiki, produced into output.

But folders are just rooms. What makes this a research operation is the employee, and every employee needs to know the rules of the house. That is one file, and it is the most important file in the whole system.

CLAUDE.md sits at the root of the vault, next to the folders, and Claude Code reads it automatically at the start of every session. You write the rules once. It follows them forever. This is the same rulebook I published in the original setup edition, unchanged, because it has not needed to change in four months of daily use.

Create a file called CLAUDE.md and paste this in:

This file tells you how to maintain this knowledge base across every session.

## Knowledge Base Rules

- This is an LLM-maintained knowledge base. You are the librarian.
- The wiki/ folder is YOUR domain — you write and maintain everything in it.
  I rarely edit wiki files directly.
- raw/ is the inbox. When I dump files here, you process them into the wiki
  during a "compile" step.
- wiki/_master-index.md is the entry point. It lists every topic folder with
  a one-line description. Always keep this up to date.
- Each topic gets its own subfolder in wiki/ (e.g., wiki/ai-agents/) with its
  own _index.md that lists all articles in that topic with brief descriptions.
- Always use [[wiki links]] to connect related concepts across topics.
- When compiling raw material:
  1. Read the raw file
  2. Decide which topic it belongs to (or create a new one)
  3. Write a wiki article with key takeaways and relevant links
  4. Update that topic's _index.md
  5. Update wiki/_master-index.md
  6. If a raw file spans multiple topics, create articles in both and cross-link
- Keep articles concise — bullet points over paragraphs.
- Include a ## Key Takeaways section in every wiki article.
- output/ is for query results and generated reports.
- When answering questions, read _master-index.md first to navigate, then
  drill into the relevant topic _index.md, then read specific articles.
- When I ask you to "compile", process everything in raw/ that hasn't been
  compiled yet into the wiki.
- When I ask you to "audit" or "lint", review the wiki for inconsistencies,
  broken links, gaps, and suggest improvements.

(First published in the rulebook section of the original setup)

Read it once and you will see what it actually is. It is a job description. Claude Code is the librarian. The wiki is its domain, not yours. When you dump reading into raw and type compile, it files everything into topics, writes the summaries, and keeps the indexes current. You never organize, never tag, never remember where you put something. The discipline that kills every note-taking system ever built is delegated to an employee who never gets bored.

And here is the part that matters beyond any single tool. Notice the filename is just a convention. Claude reads CLAUDE.md. The other agents you met earlier read the same rules from a file called agents.md. The rulebook is plain markdown, it belongs to the vault, not to the model. Hold that, it is the entire final section.

Share

Two more small files live at my vault root, and they are optional, so one honest line on each. about-me tells the model who I am, my background, what I publish, who reads it. voice is my writing DNA, sentence structure, word choices, the patterns that make a draft sound like me instead of like a model. Neither is needed for research. Both exist because I also write a social media posts out of this vault, and the moment you ask the system to draft anything public, files like these are the difference between output you publish and output you rewrite. Build them if and when you need them.

That is the entire day-one setup. Three folders, one rulebook, maybe twenty minutes. It will look almost embarrassingly small. Good. Every compounding story does.

Here is what mine turned into.

What 120 Days of Daily Use Does to an Obsidian Research Vault

Every investor knows what compounding looks like on a chart. Almost nobody thinks about what it looks like in a folder.

Four months later, the structure has grown, and nobody designed it. Daily use forced every piece of it into existence, each folder earning its place by solving a problem I actually hit. That distinction matters. A structure you design up front is a guess. A structure that grows out of real research is a record of how the work actually flows. Here is the anatomy, in the order information moves through it.

Clippings is where reading enters the system. Every article, filing, and thread I clip from the browser lands here as a markdown file. This is the folder the Web Clipper from earlier feeds. Four months of reading that would have evaporated, sitting in one place, permanently searchable.

assets exists because of one plugin doing its quiet job. Local Images Plus catches every chart and image inside anything I clip and files it here. I have never manually saved a single file into this folder, and it is now one of the heaviest in the vault. Every chart from every article I have ever clipped, owned locally, alive even after the source page dies.

raw is the inbox for everything that is not a web clip. PDFs someone sends me, exported transcripts, notes I dump in a hurry. Anything that enters the system without a home starts here.

wiki is the processed library, the clean notes the system builds out of everything above. It is the one folder I mostly stay out of, for a reason that gets its own section in a moment.

output is where the analyst’s work lands, and it changed the most. In the beginning it was a loose pile of files. Now every piece of research gets its own project folder inside output, the data pulled for it, the working files, the final memo, all living together. One project, one folder, self-contained. If you have ever browsed a well-kept GitHub repository, that is the shape, except nobody codes anything and it never leaves your computer.

That is the anatomy. But a list of folders cannot show you the part that matters, the connections. For that, Obsidian has a built-in Graph View. Every note becomes a dot, every link between notes becomes a thread, and you see your entire research life as one living network. On day one, mine was three lonely dots.

Here is what it looks like today.

In above video, you can see the same vault in motion, panning from one node out to hundreds. This is what compounding looks like when it is your own reading.

Look at what is wired together in there. Published editions connected to the filings they were built on. Company notes connected to industry notes, connected to threads clipped months apart. None of these connections were planned. They accumulated, one reading session at a time, and now every new note lands in a web that already knows its neighbors.

This is the part nobody can hand you. A vault like this cannot be downloaded, templated, or bought in a zip file. It can only be grown. And that is exactly why it is the asset that compounds while the models come and go.

Which leaves exactly one question, and it is the one this entire edition exists to answer. You now have a growing library and a rulebook that thinks like you. But the analyst reading them today is one company’s model. What happens to all of this the day a better model ships from somewhere else?

Below the line, I show you the whole answer: the ten-minute migration that moves your entire research memory, the library, the rulebook, every project folder, onto any AI model that exists or ever will, without losing a single file. It is three steps. It is the reason I stopped caring about the model leaderboard. And once you have it, you will never rebuild your setup again.

Read more

On a broking desk, insider activity arrives as a feed.

A name buys. A green row appears. A name sells. A red row appears. Somebody glances at it, says “insider buying in so-and-so,” and the row scrolls away. That was the whole ritual. The feed was the truth, and the feed only spoke in buys and sells.

I did this for months before it occurred to me to ask where the feed came from.

It comes from a filing. Every time an insider does something with their stock, they have to tell the SEC, and it’s public within two days. The feeds are just those filings, cleaned up into a table you can scan in seconds. Who, how many shares, what price. Fast and easy.

But a table can only show you what fits in a column. And there is one kind of insider decision that doesn’t fit, so the table flattens it into the most boring row on the screen.

Picture a director who is owed money. Cash. Their retainer, their fees, sometimes their actual salary. Money the company already promised them. And instead of taking it, they tell the company to pay them in stock.

Think about what that is. Not a bonus. Not shares the board handed them as a reward. A person choosing to turn guaranteed money they were owed into stock they now have to hold and hope goes up. They are giving up a sure thing for a bet. On their own company.

On the feed, that decision looks like nothing. It doesn’t show up as a buy, because technically they didn’t buy anything, they got paid. So it lands in the same dull pile as every routine “company gave an executive some shares” event, the kind of row everyone is trained to skip. The choice, the part that makes it interesting, the fact that they chose this, is written one line down in a footnote. And the footnote is the part the table never prints.

So the signal isn’t hidden. It’s worse. It’s sitting in plain sight, disguised as the most ignorable row on the screen, and the proof that it matters is a sentence nobody scrolls down to read.

I covered the loud version of this a while back. Open-market buys, the green rows everyone can see, the insider spending real cash. This is the quiet version. The buy that doesn’t look like a buy.

My last edition argued that the edge in this job was never the tool. It was the judgment you wrap around it. This one is me proving it. One loop, built in the open, every number traced back to the filing it came from, every wrong turn left in.

And the lesson isn’t how to find these. Finding them is easy, a minute of work, and I’ll show you. The lesson is everything that comes after, because the moment you actually read what surfaces, you learn that almost all of it is noise. And the one that looks like the cleanest signal of all might be the biggest trap in the pile.

In fact, I already have one in mind. Look at this.

Why the Easy Part Is Worthless

Let me show you how easy the finding is, because it matters that you see it.

There is a search box on the SEC’s own website. It reads every filing ever submitted, including the footnotes, the part the feeds throw away. It’s free. No login, no terminal, no subscription. Anyone reading this can open it right now.

So I told Claude Code, in plain English, to go use it. Not with code. With a sentence.

Find me every insider filing in the last thirty days where someone wrote that they’re taking stock instead of cash. The phrases people actually use in these footnotes are predictable: “in lieu of cash,” “in lieu of director fees,” “elected to receive.” Search for those.

It came back with a pile. Around a hundred and sixty filings once the duplicates were stripped out.

And here is the trap, the one I want you to feel before I show you the way out of it.

A hundred and sixty hits feels like a result. It feels like you found something. Your instinct, my instinct for years, is to look at that number and think the work is done. You searched, the search worked, here’s your list. Most people would stop here, post the list, and call it a signal.

That instinct is exactly wrong, and it’s the whole reason most people get nothing out of insider data even though it’s free and sitting in front of them.

Because almost none of those hundred and sixty are what you’re looking for.

The search did its job. It found every filing with the right words in it. But the right words are not the right event. A footnote can contain the phrase “in lieu of cash” and still be describing something routine, something automatic, something that isn’t a choice at all. The words match. The meaning doesn’t.

This is the part no screen and no feed will ever do for you. A search can find words. It cannot read intent. It hands you a hundred and sixty filings and it has no idea that maybe five of them mean anything. Telling those five apart from the other hundred and fifty-five is not a search problem. It’s a judgment problem. It’s the thing the machine can’t do, which means it’s the only thing you’re actually being paid for.

So the real work was never the finding. It starts now, with throwing things away.

The Three Fakes That Look Exactly Like the Real Thing

When you actually read the filings the search hands you, they sort into a few piles. Most of them are fakes. Not fakes in the sense that anyone lied. Fakes in the sense that they contain the right words while describing something that means nothing about conviction. Learning to spot them on sight is the whole skill, so let me walk you through the three that fooled me first.

The first fake is the routine grant. A company pays its directors partly in stock every single year. It’s written into the policy. Nobody chose anything. On the day the grant lands, a footnote dutifully says the shares were issued in lieu of cash, because that’s the technically correct language for how the pay is structured. The words are there. But there was no decision. The director didn’t weigh a sure thing against a bet and pick the bet. They just received their normal pay in its normal form, the same as last year and the year before. A search can’t tell the difference between a choice and a routine. You can, the moment you read it.

The second fake is the whole-board sweep. This one is sneaky because it looks like a crowd. You’ll see eight directors of the same company all “electing” stock on the exact same day. Your gut says cluster. Eight insiders, same week, same direction, that’s supposed to be the strongest signal there is. But look closer and it’s the opposite. Eight people doing the identical thing on the identical day under the identical company program is not eight opinions. It’s one corporate event wearing eight nametags. The annual meeting happened, the standing policy kicked in, everyone’s pay converted at once. There’s no individual conviction in there to find. One event, not eight. The crowd is an illusion.

The third fake is the one that nearly got me, and it’s sharp enough that it deserves its own walk-through, so I’m giving it the next section. I’ll just name it here. It’s the election that says equity and pays cash. A footnote that reads like ownership, that uses every word you’d want to see, and then, buried in the same paragraph, quietly admits the whole thing settles in money. It is a paycheck in a costume. And if you’re skimming, you will count it as a real one every time.

Here’s what survives once those three piles are swept away. A real election has a person in it. Someone who was owed cash, who could have taken the cash, and who chose stock instead, in language that shows it was their choice and not the company’s policy. Not the whole board. Not every year on schedule. A specific human being deciding to turn guaranteed money into a bet on the thing they run or oversee.

And there’s one more filter, the one that turns a real election into an interesting one. The stock has to be down.

Think about why. A director electing stock in a year the share price already doubled is electing into a party. Easy to feel good, easy to look smart, the trend is your friend. That tells you very little. But a director electing stock while the price is falling, while the chart looks ugly and the easy move would be to just take the cash and wait, that’s a different posture entirely. That’s someone reaching for more of a thing the market is actively running away from. It still isn’t proof of anything. But of all the soft signals in this pile, election into weakness is the one that’s closest to conviction, because it’s the one that costs something to make.

So that’s the target. Elective, not routine. Individual, not a board sweep. Real stock, not a cash payout in disguise. And ideally, made into a falling price.

Now let me show you that third fake up close, because it’s the one that teaches you to never trust a footnote you only skimmed.

The Filing That Says Stock and Means Cash

Here is the one that nearly slipped through, and it’s the whole reason this is a filter and not a search.

I’m not reading a hundred and sixty filings by hand. That’s the point of doing this in Claude Code. The loop pulls them, opens each raw filing, reads the footnote, and applies the test I gave it. I told it the rule up front: an election only counts if it settles in actual stock the person has to hold. If the footnote says the thing pays out in cash, throw it away, no matter how much it looks like an election.

That rule is the entire reason a company called Enviri didn’t end up on my keep list.

On the surface, Enviri was a perfect match. A director, John Quinn. An election he made as a director. A clean acquisition, 3,155 units, a little over sixty thousand dollars. Every word the search was looking for was in that footnote. If all you did was search for the words and trust the hits, Enviri goes straight onto your list and you tell your readers a director showed conviction. A lot of people would stop exactly there.

But the rule made the loop read to the end of the sentence, and the end of the sentence is where it falls apart.

The security wasn’t called common stock. The filing named it, in parentheses, right at the top: a “Deferred Stock Unit (Cash).” And the footnote said what that parenthesis meant. Each unit “represents the right to receive the value, in cash, of 1 share” of the company’s stock.

Read that twice, because the trap lives in one clause.

He doesn’t get the share. He gets the value of the share. In cash. Later.

So nothing here is what it looks like. It looks like a director turning his pay into stock he has to hold. What it actually is, is a director parking his pay in an account that tracks the share price and pays out in money down the road. He owns no shares. He holds a cash claim whose size happens to move with the stock. If the price doubles his eventual cash doubles, if it halves his cash halves, but he never owns a thing and he never put guaranteed money at the risk that real ownership means. He stayed in cash the whole time. The cash is just deferred and index-linked.

That is not conviction. It’s a salary deferral with a market-linked twist, closer to a bonus structure than a purchase. And it filed under the same words, matched the same search, and would have sat in the same pile as the real elections, if the only thing I’d done was search.

This is the trap, and it’s the single most common way the signal gets faked. It fools you precisely because nobody lied. Every word in the footnote is true. The director did elect. The units do track the stock. The acquisition is real. The one thing missing is ownership, and it’s missing inside a clause most eyes slide past: “in cash.”

There’s a softer version worth seeing too, also caught by the same rule. A different company, Mosaic, had directors who elected to take half their units as shares and half “in the form of cash.” Same trick, smaller dose. Half of what reads as a stock election is just cash in disguise. One director took thirty-five percent in cash instead. So if you’d seen his filing and thought “nice, a director backing the company,” you’d have been a third wrong, and nothing on the surface would have told you. Only the last line of the footnote does.

Now here’s the part I actually want you to take with you.

I didn’t catch Enviri by being a careful reader. I caught it because I knew this trap existed before I ran anything, and I told the loop to kill it. Read every footnote to the end. If it pays in cash, throw it out. The machine did that a hundred and sixty times without skimming, without getting bored, without missing the clause on filing number ninety-three at eleven at night.

That’s the whole shift, and it’s why I keep saying the finding was never the job.

The reading is done by the machine now. You don’t sit there with a hundred and sixty filings and a coffee. What the machine can’t do is know what to throw away. It doesn’t know that “in cash” quietly kills the whole signal. It doesn’t know a deferred unit is a paycheck wearing a costume. You know that. And the moment you know it, you can teach it once and let it run forever.

So the edge isn’t reading carefully. Everyone can read. The edge is knowing what you’re reading for, and that part still lives in your head, not in the tool.

Let me show you what that looks like on a name I’m keeping.

The One I Kept, and Why I Almost Believed It

After the fakes are gone, you’re left with a short list. Real elections, real people, real stock that actually gets held. And one name on my list looked better than all the rest.

Agenus. A small biotech. The insider was Garo Armen, and he isn’t a junior board member. He’s the Chairman and the CEO. The man who runs the company.

And the footnote was the cleanest I’d seen in the whole run. Not “granted in lieu of cash,” the passive, company-driven language that makes you suspicious. This one read: “At his request and with the approval of the Compensation Committee, Garo H. Armen’s salary is being paid in stock, in lieu of cash.”

At his request.

Not the board’s policy. Not an automatic plan. His request. The chief executive asking to take his own paycheck in shares instead of money. And not once. He did it for the pay period ending in late May, then again two weeks later in June. A standing posture, repeated. The shares are fully vested the day they’re issued, so this isn’t a deferred unit that pays out later. He owns them now. Real stock, in his name, today.

And the stock is weak. It’s the chart I showed you at the start, the one I told you to hold onto. The five-dollar stock that gave it all back and kept sliding. This is the name. He’s been electing his salary into those shares the whole way down.

The rest of this one is for paid subscribers. The turn, what survived, and the claude code repo to run it yourself.

Read more

I have never written an opinion piece here. Not once. Every edition is a workflow you can copy and a repo you can tear apart line by line.

So when I break that rule, it is worth asking why.

I broke it because of the last twelve days, and because of a word the whole timeline has suddenly fallen in love with. Loop engineering. Prompting is dead, they say, the real skill now is the loop. I will come back to that word, because the people repeating it loudest are missing what it is actually for. Hold it in your head for now.

I spent the last twelve days inside eight investment firms and family offices. They invited me in, one after another, to see what a finance person actually does with AI. Real desks. People moving real money. I went into each room expecting to walk out with something to learn.

In all eight, I saw the same thing instead.

And it had almost nothing to do with prompts, or loops, or whatever the timeline is selling this week. It had everything to do with why almost all of that noise, prompting is dead, the labs are coming for your tools, hurry up and clone the right framework, is pointing you at the wrong target.

Let me take you into the rooms.

The Prototypes Were Already Gathering Dust

The first thing I noticed was how similar the eight rooms were.

Not the offices. The offices were nothing alike. Some were glass towers, some were quiet family setups with a few people and a great deal of money sitting behind them. What was identical was the AI.

Everywhere, it was doing the same two jobs. Summaries and slides. Feed it a long report, get back a shorter one. Feed it last quarter’s numbers, get back a cleaner pitch deck. A few people had a handful of prompts they were proud of, pulled out like party tricks. That was the ceiling. Useful, real, and about two inches deep.

Then there were the prototypes.

Almost every firm had one. Not built by them. Nobody on these desks writes software. At some point someone had gotten excited, found the budget, and brought in an outside engineer or an AI person to build the thing. A screening tool. A research dashboard. An internal assistant that was going to change how the whole team worked.

And in every case the thing was sitting there, open in a tab nobody clicked, gathering dust. The software worked. It ran. It did exactly what it had been told to do. It just did not do what these people actually do all day, and so nobody touched it.

I would ask about them, and the answer kept arriving in the same shape. *It is close. It is just not how we actually do it.*

That was the tell. The prototype was not bad. In most cases it was genuinely good. They had tried to pour their own framework into it, the way they actually screen, weigh, and decide, and somewhere between what they said and what the builder understood, it got lost in translation. What came back worked. It ran. It impressed everyone for a week. But it never became the thing they reached for when a real decision was on the table, and a tool that does not touch the actual decision is a fancy monument. It sits on the shelf and gathers dust.

Underneath all of it was a posture I started to recognize halfway through the second visit. Everyone was watching everyone else. Nobody wanted to go first. They had all heard the tools change every three months, so they were waiting, scouting, holding position, hoping someone down the street would prove it worked before they risked their own desk on it. The enthusiasm was real. The movement was zero.

And the people who wanted it most, the ones who pulled me aside with their eyes lit up, asking how to actually do this, were somehow the most stuck of all.

That part bothered me more than the dust. Because the dust already had an explanation, and it was sitting in the gap between the people who knew the work and the person who built the tool.

It Was Never an Engineering Problem

Sit with that gap for a second, because it is the whole thing.

On one side stood someone who could build software but had never sat in the chair. They had never carried a position overnight, never had to defend a number to a person who could lose money on it, never felt the difference between a screen that looks right and a screen you would actually act on. On the other side stood the investor who knew all of that in their bones and could not get it out in a form that survived the handoff.

And here is the part almost nobody sees. The investor was not being lazy or vague. The knowledge that runs a real desk is the hardest kind to put into words. A good analyst does not fully know their own process. Half of it is judgment they have never once had to explain, because they have never needed to. They just do it. Ask them to write it all down for a stranger to rebuild, and most of it does not come out. So the builder built from the half that could be spoken, and the half that actually mattered stayed in the investor’s head. That is the translation gap. Not a bad engineer. Not a bad investor. A thing that does not move cleanly from one person to the other.

Now watch what every firm reaches for next. A better engineer. A more senior AI person. More budget on the technical side. It feels right and it never works, because you cannot out-engineer a translation problem. The missing piece was never engineering. Pour ten times the technical skill into the same gap and all you get is a more impressive monument gathering the same dust.

The only thing that closes it is both understandings living inside one head. Someone who knows the work and can build the loop themselves, so there is no handoff for the judgment to die in.

That person barely exists yet. Not the engineer who picked up a little finance along the way. The investor who learned to build. It is going to be one of the most valuable seats in this business over the next few years, and I will come back to why, and what it means for you, before this letter is done.

You Have Been Asking Me for Something You Already Own

Which brings me back to the word I told you to hold.

Loop engineering. Strip away the breathless part and here is all it means. The machine does a step. It checks its own work. It throws out what fails the check. It comes back to you only when something is actually worth your time. Discover, verify, filter, repeat, with a gate at every handoff and a point where it stops. That is the whole idea. It is old. The label is new. Treating it like it arrived last week is how you end up paying a premium for something you could have built quietly months ago.

Now go back to those eight rooms with this in your hand. The reason none of those prototypes were loops is the same reason they gathered dust. A tool just runs. A loop decides. And a loop can only decide well when the person who knows what counts as a real signal, and what is noise to be thrown away, is the one wiring the checks. An outside builder cannot wire judgment they do not carry. So the firms got tools that run. Not loops that decide. The deciding part never made it across the gap.

Here is the uncomfortable part, and this one is aimed at the people in my own inbox.

You have watched me work this way for months. Whatever tool happened to be in front of me, the shape was always the same. [The screen that reads the filings, throws out the noise, and hands me the names actually worth reading]. [The vault that holds everything I have ever read, so nothing leaks and the research compounds instead of scattering]. None of it was a one-off trick. It was the same loop, over and over, long before anyone bothered to give it a name. I never called it loop engineering because it did not need one.

So when readers message me asking me to build them a loop engineering research workflow, I am not quite sure how to answer. It is already in the archive. You are asking me for something you already own.

Which leaves the only question that actually matters. If the loop is not the hard part, and the tool is not the edge, and the prompt everyone is now declaring dead was never the thing carrying the weight, then what is. That is the rest of this letter.

A Perfect Buffett Prompt Still Fails in Your Hands

Let me make the other side’s case first, because it is stronger than most people admit.

AI is going to eat the commodity layer of this work, all of it. The summaries. The screens. The extraction. Reading a three-hundred-page filing in a minute. Pulling a debt schedule, computing a fifty-year ratio, lining up ten comparables before you have finished your coffee. That is real, it is already here, and it is most of what those eight firms were using it for. Anyone who tells you AI will not flatten that layer is selling you something.

And the labs are not stopping at the inputs. They are now shipping the judgment layer too, or trying to. Pre-built financial-services agent templates aimed at banks, insurers and asset managers. Managed deployments inside the big consulting firms. The pitch is that you will not even need to build the loop, because a polished one will arrive in a box with your logo on it. So the honest version of the bear case is not just that the easy part gets commoditized. It is that the hard part is next.

Here is why I still think it is wrong.

Mohnish Pabrai built his entire public reputation on cloning. Copy the best investors, feel no shame about it, the idea does not have to be yours. He says it openly. And then, in the same breath, he draws a line most people skip right past. Once you see the idea, he says, you do all your own work, your own research, you make sure it is something you understand, you make sure it sits inside your circle of competence. Read that again. The most quotable champion of copying on earth is telling you the idea clones, and the work does not. You can lift the what. You cannot lift the who.

That is the whole thing. A perfect Buffett prompt is a cloned idea. Hand it to me and it does not become Buffett’s judgment, it becomes a very confident set of instructions pointed at a circle of competence I do not have. I wrote this once and I still believe it. Borrowing someone else’s investment skill is like wearing someone else’s prescription glasses. For two minutes you feel sophisticated. Then you realise you cannot see properly.

I have said this another way before, and I will say it again here because it is the hinge of the whole argument. Two successful investors can agree on eighty percent of the principles and still work completely differently, because the way they extract information, the way they connect dots, the questions they keep asking and the things they choose to ignore are never the same. You cannot inherit that from a zip file.

So when the labs ship you a research agent in a box, you are buying a cloned idea with a logo on it. It will be good. It will be fast. It will do the commodity layer beautifully. And it will work for everyone who buys it identically, which is exactly why it cannot be anyone’s edge. The moment a framework is packaged and handed out, its edge expires.

A quant I read said it cleanly: borrowed approaches expire when everyone else adopts them. The generative thing, the part that keeps producing new angles, is the part that was never in the box.

There is a second way frameworks fail, and it is quieter, because it is not about people at all. It is about time.

You have heard someone say the gold-to-silver ratio is high, so silver is cheap, sell when it reverts. They will hand you fifty years of data to prove it. But fifty years ago silver was mostly a monetary metal. What industrial demand it had ran through photographic film, and then digital cameras quietly erased most of that overnight. Today the demand has come back in a completely different form, wired into solar panels and electronics and EVs at a scale that did not exist when the ratio was first worshipped. The number still computes. It is just quietly measuring a thing that no longer exists in the same form. And I want to be careful here, because the failure is not using history. History gives you base rates and cycles, and the best investors lean on them hard. I lean on them so hard that when I built [my framework for researching any industry from scratch], the very first pillar, before growth, before unit economics, before a single number, was simply this:

how did we get here. The origin. You cannot read an industry until you understand the forces that shaped it. So history is not the enemy.

The failure is making it the final step. A fifty-year backtest is a cloned past, and the world it was cloned from changed underneath it while no one was looking.

Notice that AI is brilliant at exactly this layer. It will pull the fifty years and compute the ratio in seconds. Which is the entire point. If the machine can clone the past instantly, then the past was never the edge either. The edge is knowing when the regime broke. That is not in the data, and it is not in the prompt. It is in you.

So both clones fail the same way. The Buffett prompt is a framework that does not transfer across people. The gold-silver ratio is a framework that does not transfer across time. AI makes both clones free, and free is the tell. The thing it cannot copy, the judgment about which idea is real, which number still means what it used to, what to throw away, is the only thing left that was ever worth anything.

Which raises the obvious question. If you cannot buy the edge, and you cannot download it, and you cannot inherit it from a zip file, then where does it actually come from, and what are you supposed to do about it.

That is the part I have been building toward this whole time.

Build the Loop Around Yourself

So where does it come from.

It comes from the one place nobody can ship you. The work you have already done, the cycles you have already sat through, the questions you cannot stop asking, the things you instinctively ignore. Everything that got engraved into you slowly, over years, while you were not trying to turn it into a product. That is the circle of competence Pabrai was pointing at. It is not downloadable because it was never written down. It only exists as you.

The mistake almost everyone makes from here is to go looking for a better framework to copy. A sharper prompt. A more complete skill. Someone else’s system that finally works. I have watched smart people lose a year to this, hunting for the perfect borrowed process, and it never arrives, because the thing they are missing was never going to come from outside.

I have said this before, and I will keep saying it. A skill will not make you a better investor. Building your own, badly, watching it fail on a real thesis, and fixing it run by run, just might. Not because the file is valuable. Because by the third version, the clearest thing in the room is not the skill. It is your own process, finally written down where you can see it.

That is the real reason to build your own loop. Not because the loop is magic. Because building it is the only thing that forces the engraved, unspoken half of your judgment out of your head and into something you can run. The loop is just the excuse. You are the output.

And this is where the eight rooms come all the way back. The reason those prototypes gathered dust was that someone tried to write down a process they did not own. You will never have that problem with your own. You are not translating across a gap. There is no gap. The person who knows the work and the person building the loop are the same person, sitting in the same chair. Nothing gets lost, because nothing has to move.

That is the seat I told you we would come back to. It barely exists today. The investor who learned to build, who can take the judgment that lives only in their head and wire it into a loop that runs while they sleep. Not the engineer who studied some finance. The other direction. And I think over the next few years it becomes one of the most valuable profiles in this entire business, because it is the one profile that cannot be handed to anyone else.

Let me kill the obvious objection, because someone at one of those eight firms will raise it. The labs are coming for this too, they will say. They are already shipping research agents in a box, managed deployments, templates with your logo on them. Will they not just commoditize the build-your-own act as well.

No. They will commoditize the loop. They cannot commoditize what you point it at. A boxed agent is the most cloned idea of all, the same one sold to every firm on the street, which is exactly why none of them can build an edge on it. The lab can hand you a better engine every quarter. It cannot hand you the circle of competence to steer it. That part still has to be yours, and the better their engines get, the more the only scarce thing left is the judgment driving them.

There is one more reason this is worth starting now, and it is the part most people get backwards. The tools are not going to settle. They will get better every month, for years. Most people hear that and freeze, waiting for the dust to settle before they commit. But if the edge is the judgment you wrap around the loop, then a moving toolset is not a threat. It is leverage that compounds. Every upgrade makes your engraved judgment worth more, not less, because there is more horsepower behind the same irreplaceable hand on the wheel. The people waiting for it to stabilize are waiting for the one thing that gives them an advantage to disappear.

So stop hunting for someone else’s framework. Build your own loop, badly, around the one thing you already have that nobody can clone. Then let the tools race. You are the part that does not expire.

Enough Opinion. Here Is the Proof.

I have argued this long enough.

And argument is not what you come here for. You come here to watch the thing get built, then tear it apart yourself. So I am going to stop talking about loops and judgment and go do the only thing that has ever made this case for me. Build them in front of you.

This is the start of a series. Not a content calendar, a proof. Each edition is me taking some piece of judgment that lives only in my head and wiring it into a loop you can watch run, end to end, mistakes left in. You do not have to believe a word of the argument above. Watch me build, and decide for yourself whether the engraved part actually survives the trip into the machine.

Three are coming.

First, the insider signal your data feed deletes before you ever see it. Not the open-market buys everyone tracks. The quiet election, buried in a single Form 4 footnote, where a director quietly swaps guaranteed cash for stock. No vendor surfaces it. I will show you the loop that finds it, throws out the fakes that fool a naive screen, and hands back only the few worth a second look. Then I will tell you what those names did.

Second, Obsidian as the brain that any model can plug into. Not Claude only. Whatever runs best next month. The library sits still while the model behind it changes, and I will show you why the brain, not the model, is the part that compounds.

Third, the full loop engineering setup for investment research, start to finish. The thing readers keep asking me to build for them. The whole loop, in one place, so you can stop asking and start building your own.

I cannot hand you my loop. You already know that is the whole point. But I can build mine in the open, one edition at a time, and show you exactly where the judgment goes in. The rest is yours to engrave.

Before I Close

A quick, honest word about where the ideas in this letter came from, because the whole argument is that nobody does this alone.

The view that your edge is the slowly engraved version of you, not the tool in your hand, I have been circling for months in this newsletter. But the sharpest writers I read keep saying it better than I do, and the quants thinking out loud about loops put words to a thing I was already doing without a name. I steal from people smarter than me. That is not a confession. It is the method. The only original part is what survives my own pass.

Which is exactly what is coming, beyond the three editions above.

I am also starting something I have wanted to do for a long time. Real deep dives, on real companies, mostly the small and micro caps nobody else is bothering to cover. The kind of approach you already know, because it is the one I keep teaching. I find an idea from an investor sharper than me, on X, in a newsletter, in the rooms where good investors talk. Then I do the part most people skip. I run it through my own forensic process, AI doing the heavy lifting in the middle, and I find out whether the idea actually survives.

Because here is the belief under all of it. AI is not going anywhere. The only question left is how you use it. Almost everyone is using it to replace their judgment, let the model pick the stock, let the model tell them what to think. That is the fast way to be wrong with confidence. I use it the other way. To amplify what I can already do, not to do it for me. The view at the end is mine. The machine just got me there faster.

Idea to verdict, the whole thing in the open, a couple of times a month. Including the ones that fail my check, because a killed idea is often the more useful read.

None of this replaces the workflows. The frameworks are not going anywhere. This is on top.

So that is the plan. Less of me arguing, more of me building, and now some of me actually putting it to work on live names. If you have been reading this far, you are exactly who I write for.

Would you read it? Tell me. And if a sharp investor or a desk you respect should see this, send it their way. That is the only way this circle grows.

Disclaimer: Alpha with AI covers US-listed and other global securities for educational and research purposes only. Nothing here is investment, legal, or tax advice. AI-assisted analysis can be wrong, and every figure worth acting on should be checked against the primary filing yourself. Always do your own work and consult a qualified professional before making any investment decision.

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

Financial Clarity. Insightful Ideas.

Get 25% off for 1 year

We went paid three weeks ago. The response has been more than I expected.

Since then I have received messages I did not expect, not about the content, but about access.

A few days ago, a reader in Ghana wrote to me. They had been reading the free editions, found them extremely useful, and wanted to go paid. But the pricing page meant something very different in their economy than it does in New York or London.

It was not a complaint. It was one of the most thoughtful messages I have received since starting this newsletter.

It made me ask a question I should have asked on day one.

A Question I Should Have Asked on Day One

The question was simple.

Should access to quality research depend on where you live?

I already knew the answer. I just had not built around it yet.

So here is what we did.

If you are permanently located in a developing economy, including but not limited to India, Ghana, South Africa, Nigeria, Kenya, Brazil, Indonesia, the Philippines, or similar regions, just reply to this email, or write to us at info@shikshannivesh.com. Share your country, and we will work with you on adjusted pricing that fits your local purchasing power.

We will verify this through your payment details to keep the system fair for everyone. That is all it takes.

This is not a discount. It is what fair access looks like when your readers are spread across 50 countries, and a dollar is not worth the same in all of them.

Another Way In, and It Is Free

There is one more way to get full access, and it does not cost anything.

We just launched a referral program.

• Refer 7 readers, and you get one month of paid access.

• Refer 30, and you get three months.

• Refer 50, and you get six months.

If you know other investors or analysts who would find these editions useful, share your referral link with them. When they subscribe, the months are yours.

Terms apply, mostly to keep out spam and keep the program fair. But if you genuinely share work you believe in, this is the simplest way to earn full access without paying for it.

One More Way, If You Want Everything

And if you want the whole system, the Alpha with AI club premium membership now includes a complimentary subscription to this newsletter.

So premium members get the weekly playbooks, the community of 100s of global analysts, and every edition here, together.

Club Link

Four Ways In

When I started this newsletter, I wanted to make institutional-grade research accessible to people who were never handed it.

The message from Ghana reminded me that accessible has to mean accessible everywhere.

So there are four ways in now.

Upgrade at the regular price, the same one on the subscription page.

If you are based in one of the developing economies mentioned above, just reply to this email, or write to us at info@shikshannivesh.com, and we will adjust it for where you live.

Earn months of access by referring readers who would value this work.

Or join the Alpha with AI club premium and get this newsletter included with everything else.

The work behind the paywall is the same either way. The only thing that changed is who can reach it.

Disclaimer: Alpha with AI covers US-listed and other global securities for educational and research purposes only. Nothing here is investment, legal, or tax advice. Always verify against primary sources and consult a qualified professional before making investment decisions.

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

Financial Clarity. Insightful Ideas.

For years I traded off one number. The estimate.

Consensus said a company would earn this much. Analysts said buy, hold, or sell. I positioned around it, and so did everyone else on the floor. The entire job was reading what a room full of analysts thought a company was about to do.

It took me an embarrassingly long time to see the obvious problem.

The analysts were guessing. They had the same filings I had, the same models, the same blind spots. When they were wrong, they were all wrong together, and I was wrong right alongside them. I was spending my days reading the forecasts of people standing outside the company, trying to predict the inside.

Nobody around me was watching the one group that already knew the answer.

The company itself.

I learned this years later, on a broking desk in Bombay, from an older trader who barely looked at estimates. He watched what companies did after they reported, not what analysts predicted before. And he showed me a tell I have never been able to unsee since.

A company that just had a great quarter wants the whole world to look. The moment the numbers are out, it fills its calendar. Investor conferences, fireside chats, webcasts, roadshows, one after another for the next month and a half. It is throwing a party and sending invitations.

A company that just had a bad quarter does the opposite. It goes quiet. The calendar empties out. Fewer events, less marketing, a schedule with suddenly nothing on it. It is not hiding the numbers, those are already public. It is hiding from the conversation about them.

The company is voting on its own quarter with its own calendar. And that calendar is public, sitting on the investor relations page, weeks before any analyst updates a model.

Once you see it, you cannot stop seeing it. A full post-earnings calendar is confidence. A bare one is fear.

The best part is what comes next. This is not a read you do once, on one stock. It is a read you can run on every company you will ever hold, on every quarter, for as long as you invest. The same tell, the same hour after earnings, forever.

So I built it into something I can point at any ticker on demand. Take Lululemon. It just cut its guidance, the whole street turned against it, and Michael Burry started buying it anyway. I am going to run my whole read on it in front of you, live. I used Claude Code for this, but if that word makes you nervous, you can do the same thing in Claude Cowork. It is plain English the whole way down.

Why a Beat Throws a Party and a Miss Goes Dark

Think about what a company actually controls after it reports.

It does not control the numbers. Those are set the moment the quarter closes. It does not control what analysts write, or where the stock opens the next morning. All of that is out of its hands by the time the press release goes out.

But it controls one thing completely. Its own calendar.

In the weeks after earnings, management decides how visible it wants to be. It chooses whether to show up at the big bank’s tech conference. Whether to host a fireside chat. Whether the CEO sits for a webcast, whether the CFO goes on a roadshow, whether the investor relations team books anything at all. Every one of those is a choice, made by people who saw the full quarter before anyone outside the building did.

And here is the thing about people who feel good about their work. They want to be seen doing it.

A company that just beat, raised guidance, and likes its own story cannot wait to get in front of investors. It books everything. The four to six weeks after the print fill up with appearances, because every appearance is a chance to repeat a good story to the exact people who move the stock. A strong quarter wants an audience.

A company that just missed, or guided down, or knows the next quarter looks shaky, has the opposite instinct. Every investor event is now a room full of people asking the one question management does not want to answer. So the events quietly do not get booked. The calendar after a weak quarter is thin, not because nothing is happening, but because management has nothing it wants to stand up and defend.

This is not a theory about what companies should do. It is a pattern in what they actually do, and you can watch it happen in public. The investor relations page lists every scheduled event. The conference organizers publish their speaker lineups. None of it is hidden. It is just that almost nobody reads a calendar as a signal, because we are all trained to read the forecast instead.

That older trader’s whole edge was reading the thing everyone else ignored.

One honest caution before we go further, because I will not sell you a crystal ball. This is a tell, not a guarantee. A light calendar can mean a company in a quiet period, or one that simply does not market much. A packed one can be a coincidence of conference season. The signal is real, but it is one input, the same way insider buying is one input, the same way price action is one input. You stack it with everything else you know. Used that way, it is one of the cleanest free reads available to a retail investor, and until recently it was buried in work nobody wanted to do.

That last part is what changed.

The Four Things You Actually Read

The tell is simple. Reading it well comes down to four questions, asked in order.

One thing before the questions, so you know what you are looking for. This will not predict the quarter for you. What it does is catch the moments when a company’s behavior contradicts its own story, and that gap is usually the thing worth knowing.

One. How full is the calendar right now?

Go to the company’s investor relations page and look at the four to six weeks right after the earnings date. Count the scheduled events. Conferences, fireside chats, webcasts, an investor day, the non-deal roadshows that brokers host where management spends a day meeting investors without raising a dollar. Any appearance where management stands in front of the people who move the stock. That number, on its own, tells you something. A handful of events is a company that wants to be out there. A blank stretch is a company that does not.

Two. Is that more or less than the company’s own normal?

This is the move most people miss, and it is the one that matters most. A calendar with three events means nothing in isolation. Some companies are just busier than others, and many have a rhythm to their year, a heavy season and a quiet one. So you do not compare this quarter to last quarter and stop. You compare it to the same post-earnings window across the last four or five quarters. That history is the company’s baseline. Now this quarter has something to be measured against. If a company that reliably booked four or five appearances after every recent print suddenly has one, that drop is the signal, and you can trust it is a real change and not just the slow season. You are not reading the calendar. You are reading this quarter against everything the company normally does.

Three. What did management actually guide?

The calendar tells you whether management wants to be seen. This tells you what management said when it had to speak. On every earnings call, management gives a forward number. Revenue for next quarter, a full-year range, a margin target. That number is a promise, and a promise is only worth the track record behind it. So you do two things. You read the latest guidance, up, down, or held. Then you check the last several quarters of guidance against what the company actually delivered. A management team that quietly walks its full-year number down, after a history of hitting its targets, has just told you something the headline number did not. A team that always sandbags and then beats is playing a different game, and you read a soft guide from them differently. Guidance without the track record is noise. Guidance against the track record is signal.

Four. What does the street believe, and is anyone betting the other way?

The first three moves tell you what the company thinks of itself. This one tells you what everyone else thinks, so you can find the gap. Pull the current analyst picture. Count the buys, holds, and sells. Look at the average price target against where the stock trades now. You are not looking for the rating. You are looking for disagreement. A company going quiet on its calendar, after cutting its own guidance, while analysts have already abandoned it, is one kind of setup. The same company with one famous investor loudly buying into all of that is a far more interesting one. When the behavior, the guidance, the consensus, and a contrarian all point in different directions, you are not looking at a stock. You are looking at an argument. And arguments are where the money is.

That is the entire read. Calendar now, calendar against its own history, the guidance and the track record behind it, the consensus and whoever is fighting it. Four questions, every one of them answerable from public pages.

Share

Lululemon is sitting in exactly this kind of argument right now, which is why I picked it. It cut its full-year guidance and warned on the next quarter. The street has all but given up, has pointed out that of the thirty-two analysts covering it, only two rate it a buy, the most negative consensus he says he has seen for a company in this shape. And Burry whose Substack I read, has been buying it on the way down, calling the gloom overdone. published a deep-dive on it too, worth your time if you want the long version. Four signals, four directions, one stock. The perfect thing to point a fresh read at.

Here is the catch, and it is the only honest objection to any of this.

Done by hand, this is an afternoon. You are clicking through an investor relations site, copying event dates into a notepad, going back five quarters and doing it again, then reading four earnings calls for the guidance, then opening three more sites to rebuild the analyst picture. By the time you finish for one stock, the moment has cooled, and you have one stock. Nobody runs this on their whole watchlist by hand. That is exactly why the signal stays underused, sitting in plain sight, ignored because the reading of it is tedious.

So I stopped reading it by hand.

What follows is the same four questions, handed to an AI that does all of it in one pass, on a stock with the whole street on one side and Burry on the other, every number traced back to a public source you can check yourself.

The Whole Thing Is One Paragraph You Type in Plain English

This is the part where most newsletters hand you a six-hundred-word prompt with roles and rules and capital letters. I am not going to do that, because the entire reason to run this inside Claude Code is that you can just talk to it.

So here is the actual thing I typed. One paragraph, plain English, the way I would explain the job to a junior analyst sitting next to me. Read it once and you will see all four moves living inside it, in order, without a single bullet point.

Look at Lululemon, ticker LULU. It just reported and cut its full-year guidance. I want to know how the company is behaving after this quarter, because companies that feel good about a quarter fill their investor calendar and companies that don't go quiet. So first, go to its investor relations page and any conference schedules you can find, and list every investor event on the calendar in the four to six weeks after the earnings date. Then do the same thing for the last four or five quarters, the same window after each earnings date, so I can see whether this quarter is busier or quieter than the company's own normal. Next, read the latest earnings call and tell me exactly what management guided for next quarter and the full year, and compare that guidance to what they guided and then actually delivered over the last few quarters, so I know whether this is a team that keeps its word. Finally, pull the current analyst picture, how many buys, holds and sells, and the average price target versus where the stock trades now. Cite a public source for every number, and if anything isn't disclosed, say so instead of guessing. At the end, give me a plain-English read: is this company acting confident
or acting scared, and where does its behavior disagree with what the street believes?

That is it. No setup, no persona, no formatting instructions. You could read that paragraph out loud to a person and they would know exactly what to do. That is the whole point. The model does too.

Notice what is hiding inside it. The first sentence is move one, the calendar now. The second is move two, the calendar against its own history. The third is move three, the guidance and the track record behind it. The fourth is move four, the street and the gap. The four moves are the framework. The paragraph is just the framework spoken like a human.

And here is the part I want you to take even if you stop reading here and never open Claude Code. You do not need the tool to use the idea. You can paste that paragraph into plain Claude or any CLI you already use, change the ticker, and get a usable read on any company you hold. The framework travels. The tool only makes it faster and lets you point it at ten names instead of one.

When I ran this on Lululemon, here is what came back.

I Pointed It at Lululemon. It Told Me My Own Rule Was Too Simple.

Here is the part I did not plan for.

I expected a clean win. Lululemon had just cut guidance, the street had turned, the story looked broken. The tell predicts a company in that spot goes quiet, empties its calendar, hides from the conversation. I pointed the read at it expecting to watch the calendar thin out and prove the whole thing in one screenshot.

That is not what happened. And what happened instead is worth more than the clean win would have been.

First, the run. Three ways to do this yourself, pick the one that scares you least. Open the Claude desktop app and use Claude Code or Cowork, no terminal, paste and talk. Or run it the way I do, inside Obsidian, with the terminal plugin installed from community plugins so Claude Code works right next to your notes. I walked through that whole setup in how I set up Claude Code as my investment research analyst and the Obsidian layer in the part four edition. Or if you live in a terminal, use Codex or any CLI. The paragraph is identical everywhere.

I pasted the paragraph from the last section, the plain-English one, swapped in nothing, and let it work.

The entire run, start to finish, nothing cut. This is the whole process behind the read below. Watch it pull five quarters of investor events on its own.

It did not answer from memory. It fanned the job out, hit the investor relations page, the press releases, the conference schedules, the transcripts, and pulled five quarters of history before it said a word. The whole session is in the repo, every source link intact, so you can check any number I am about to show you.

Then the answer came back, and the first thing it told me was that my hypothesis ran straight into a structural fact. Lululemon barely uses its investor calendar in any quarter at all.

Move one and two, the calendar. Here is what it actually counted, the events in the four-to-six-week window after each of the last five earnings dates:

Read that and the naive version of my tell falls apart. The most recent quarter has two events, tied for the busiest of the five. If I had just counted events, I would have concluded Lululemon was feeling confident. The opposite of the truth.

The reason is the thing the model caught and I had not thought about. Some companies barely market to investors at all. Lululemon does not press-release its conference appearances. Its calendar is almost always near-empty, so there is nothing left to thin out. Run a raw event count on a company like this and the signal is just noise.

This is the moment the run earned its place in this edition. Because then it found the actual signal, the one hiding underneath the count.

The real tell was not how short the calendar got. It was what the company refused to add to it. A business down around 60 percent over the year, run by an interim team, fighting a proxy battle, did not schedule a single voluntary thing. No analyst day. No special investor update. No bonus conference circuit to stand up and defend the story. It did the legal minimum and nothing more. One of its two events this quarter was a mandatory annual meeting, and this year that meeting was a contested proxy fight tied to a Chip Wilson cooperation agreement. The company was forced into that room. It did not choose to enter it.

So the tell was right. My way of reading it was too crude. The company was hiding. It just did not need to empty a calendar to do it, because the calendar was already empty. You read the silence against the situation, not the event count against last quarter. That correction is the whole reason I am glad I ran this live instead of writing it from theory.

Move three, the guidance, and this is where the run got sharp. This is the move you would never get from counting anything. The model read the last five quarters of guidance against what the company actually delivered, and found a split that tells you exactly how much to trust management.

Every single quarter, for five quarters running, Lululemon beat the top of its own EPS guide. Five for five. This is a team that always clears the bar it sets for the next ninety days.

And across that same stretch, it cut its full-year guidance three separate times. Beat the quarter, lower the year. Beat the quarter, lower the year. The pattern in one line: they keep their word on the short bar they set low on purpose, while the real trajectory of the business grinds down underneath them.

That is the difference between a management read and a headline. The quarterly guide is a sandbag they will probably clear again next print. The full-year guide is the one quietly telling you the franchise is deteriorating. Trust the short word. Distrust the long one.

Below the line is where this resolves. The full analyst picture and the one tension buried inside it that I think matters more than the guidance cut itself. The exact point where management’s story and the market’s story split clean in two. What Michael Burry is seeing here that the entire sell-side is not. The plain-English verdict on whether this company is acting confident or acting scared. And the finished read you can point at any stock you hold, with the whole conversation and every sourced link in the repo.

This is where the paid section begins. The free half gave you the method and the full live run. The verdict, the analyst picture, and the saved skill are below for paid subscribers. If this is the kind of work you want every edition, consider subscribing.

Read more

Nobody teaches you what to do on the day your stock breaks.

There are thousands of newsletters about investing. I write one of them. We teach frameworks, checklists, workflows. All of it built on problems someone already solved.

Then a week like this one arrives.

Broadcom, one of the ten largest companies in America, is down 8.5 percent over the past month. That number sounds manageable until you see how it happened. Almost all of it came in the last five trading days, a drop of roughly 20 percent.

The stock spent most of the month going up and then lost a fifth of its value in under a week. The whole chip space went down with it. If you were holding it, you were not thinking about frameworks. You were staring at a red screen after lunch, asking the three questions every holder asks and no one answers in advance:

Is it my stock? Is it my sector? Or is the whole market breaking?

Here is the uncomfortable truth about investing content, including mine. We teach solved problems. Your portfolio produces unsolved ones.

That gap is not your fault. No writer can cover your problem before it happens. The market invents new ones faster than anyone can publish.

So this edition is different. I am not handing you a prompt for this situation. I am going to build the answer in front of you, the same evening the problem showed up, using a stock I had never researched in my life until this week. And then I am going to show you the part that actually matters: the method underneath, the one you will reuse next month on a problem nobody has written about yet.

Solved problems make you informed. Unsolved ones make you money. This is how you work on the unsolved kind.

I Already Wrote This Edition Once. It Could Not Help Me This Week.

In November I published an edition about exactly this situation. An Indian stock called Power Finance Corporation had dropped 8 percent while its sector barely moved, and I showed you how to diagnose whether the problem was the company, the sector, or the market. You can read the whole edition here.

That edition had a 600-word prompt. It asked you to download two CSV files from the Indian stock exchange first. Then you pasted everything into an AI and waited.

It worked. Readers ran it. I was proud of it.

This week I went back to it, and I saw it for what it was. A solved problem, frozen in place. The prompt knew the Indian market. It knew NSE data files. It knew nothing about Broadcom, US sector funds, or where American capital hides when it gets scared. My own prompt could not help me with my own framework.

That is the problem with prompts. A prompt is an answer. It answers the exact problem it was written for, and nothing else.

And investing problems do not repeat politely. They come back wearing a different ticker, in a different market, with the data living somewhere new. Whatever hits your portfolio next month will not match anyone’s template. Including mine.

So this time I am not handing you the answer. I am going to show you how the answer gets built. The whole thing took one evening.

I used Claude’s new model, Fable 5. You may have seen it called Mythos 5, it is the same model. And I ran it inside Claude Code, directly in the Claude desktop app. If you have the Claude app on your computer, you already have everything I used. No terminal. No installation. Open the app, and Claude Code sits right there next to Cowork. (If you want the heavier setup I personally run, terminal, Obsidian vault and all, that is its own edition here.)

What follows are the five instructions I typed, in order. Each one is plain English. Each one carries a principle you will reuse on problems I will never write about.

But first, the three questions everything hangs on:

1. Is my stock weak on its own?

2. Is my sector shifting?

3. Or is the whole market repricing?

Before I show you a single number, commit to an answer.

Share

The Build, In Five Moves

What follows is the entire session, in order. Five instructions, typed in plain English, inside Claude Code in the Claude desktop app. Each move carries a principle. The principles are the edition. Broadcom is just the example.

The whole session is also here as an 8-minute recording, uncut, nothing edited out. My suggestion: read the five moves first, then come back and watch it once you know what you are looking at. The moment the data source dies and the model reroutes itself is worth seeing with your own eyes.

Watch for: the model designing the data plan from three questions, the data source dying and the self-reroute, the patch on 48 files, the verdict, and the skill being written at the end.

Move One. State the problem, not a prompt.

In November I would have started by writing a prompt. Role, inputs, computation steps, output format, NA rules. Six hundred words before the AI did anything.

This time I typed this:

Tech is selling off this week and Broadcom has dropped around 20 percent in five days. I want to answer three questions: Is Broadcom weak on its own? Is the whole sector breaking down? And where is the money actually going? Before you do anything, tell me exactly what data you would need to answer these three questions properly, and where you would get it from.

Notice what that last sentence does. It does not ask for analysis. It asks for the data plan. Most people skip this and jump straight to the answer. The data plan is where the quality gets decided.

Full output:

data-plan.md

What came back was a better research spec than my November prompt. For question one, it wanted Broadcom’s prices and volumes, the same series for six direct peers, and the news flow around the drop. Then it added something I had not asked for: beta context. Broadcom moves more than its sector on a normal day, so a sector drop already explains part of any Broadcom drop. The real question is the residual, the part the sector cannot explain.

For question two, it refused to judge a sector by one stock. It wanted breadth, what fraction of the chip names are actually down, and it wanted equal-weight versus cap-weight tech, because a megacap problem and a sector problem look identical in the headline index.

For question three, it opened with a caveat I want to frame: every share sold is a share bought. “Where is the money going” is really two measurable things, what is catching a bid, and where fund flows land. It flagged in advance that hard flow data lags by days and everything before that is inference from prices.

My November prompt had none of this reasoning. It had my instructions, frozen. This had thinking, because I handed it questions instead of commands.

Move Two. Files, not memory.

The single biggest source of AI errors in finance is letting the model carry numbers in its head. Numbers read off webpages, half-remembered from training, blended across dates. So the second instruction set one rule for the rest of the session:

Good. Pull all of it. Two rules. First, everything lands as files in a dated data folder: daily closing prices and volumes as CSVs going back about three months for every ticker and ETF you listed, and the news timeline and any ETF flow findings as a markdown file with the source of every item. Second, from here on, every number we use must come from these files, not from memory or a web page.

Then I watched it work, and this is the part no demo video shows you, so I am leaving it in.

Its first-choice data source turned out to be blocked behind a JavaScript wall. It fell back to Yahoo Finance’s API, which rate-limited it. It fell back again, to the yfinance library, which worked. Then its integrity scan caught that Yahoo had not yet backfilled the previous day’s close, so the latest row of every file was empty. It patched all 48 US-listed series from a different endpoint, verified the dates, and documented the patch in a README. Then my Firecrawl ran out of credits mid news-pull and it switched to built-in web search without being told.

None of this was my plan. All of it is why the workflow survives contact with reality. Twenty minutes later the folder held 50 price files covering 64 trading days, a news timeline where every single item carries its source link, and a README documenting where every number came from, including the patch.

That folder is the product. Everything after this is just reading it. The full folder is in the repo:

repo link

Move Three. Models interpret. Code computes.

I had the third instruction ready in my notes. Here it is, exactly as I planned to type it:

Now compute from the files: returns over 1 day, 5 days, 1 month and 3 months for Broadcom, its sector benchmarks, all the major sector ETFs and the safe-haven assets. Also compute Broadcom’s return minus its sector’s return, 20-day volume z-scores for the sector’s top holdings, and sector breadth, meaning what percent of holdings are positive. Do all of it in code and save the result tables as files.

I never got to type it.

The moment the data folder was full, the model went ahead and computed all of it on its own, in code, and saved the tables next to the prices. Not because it read my mind. Because the rule I set in Move Two, every number must come from these files, left it no other way to proceed. Set the architecture right and the discipline follows without being asked.

In November, the AI did this arithmetic in its head, reading numbers off pages and calculating returns as a language model, which is exactly where language models are weakest. The wall of warnings in my old prompt existed to compensate for that. This time the arithmetic never touched the model. A script ran on the folder. Same input, same output, every time.

Here is what the files say, and I am giving you the exact figures because every one of them traces to a CSV in the repo:

Broadcom fell 18.6 percent over the five days. Its sector fund, SMH, fell 6.5 percent. Broadcom’s beta to its sector, measured on the three months before the event, is 0.76, which means the sector’s week only explains a 4.9 percent drop. The residual, the Broadcom-specific part, is roughly 13.6 percentage points. And it happened on volume running at 2.2 times the three-month average. That is not drift. That is conviction selling.

The sector table is just as blunt. 22 of 25 chip names down on the week, median minus 6.3 percent. Equal-weight tech fell as much as cap-weight tech, 8.9 versus 8.8 percent, so this was not just a megacap story. And yet: every benchmark, SMH, SOXX, XLK, QQQ, SPY, still sits above its 50-day average. Every one except Broadcom itself.

Move Three output key-stats.md

Below the line: the verdict on all three questions, the poll resolved, the moment the model audits my own rules and finds where they are blind, the fourth classification that did not exist this morning, where the money actually went, and the finished skill you can install and run on any stock you own.

Read more

A reader messaged me last week and asked if I’d break down the SpaceX IPO.

I almost said no. Not because it isn’t interesting. Because I don’t write about whatever is trending that week. Trends rot. In AI especially, the hot thing today is stale in three days, and I’m not interested in teaching you something with a shelf life. I write about workflows that still matter a year from now, and I usually find them buried in messages like this one, from readers telling me what they’re actually stuck on.

This one was worth it. Because SpaceX isn’t really the lesson. The lesson is the document.

I’ve admired this company for years. Not Musk the personality. The work ethic, the engineering DNA. There’s a story about how that DNA works that has stuck with me for a long time.

An engineer comes to Musk and says he needs to buy a part. It costs $1,200. Musk doesn’t ask why they need it. He asks what it’s made of. Some kind of metal, they say. He asks what that metal costs. They check the London Metal Ex…

Read more

I have been in the equity market since 2018. I still make mistakes every single day.

I do not say that the way people say it when they want you to think they are humble. I say it because it is the truest thing I know about this business. I make a mistake, I sit with it, I rethink it, I learn the lesson, and then I make a slightly different mistake the next week. That is the whole job. Anyone who tells you the best investors stop making mistakes has not watched the best investors closely enough.

Look at Mohnish Pabrai and Micron. One of the sharpest value investors of his generation sold most of his Micron position in 2023, before one of the great runs in semiconductors. That is not a small investor fumbling. That is a master of the craft, and the market still handed him a regret he…

Read more

During COVID, I screened the market every single morning.

I had no idea what I was doing.

I’d read something the night before, some ratio, some filter, some “this is what the great investors look at,” and by 9am I’d run the entire market through it. The next week I’d read something else, and the screen would change completely. The parameters I trusted back then make me wince now.

But it felt like work. It felt like being a real investor. Screen, shortlist, open the annual report of whatever came out on top, repeat. I was busy from open to close, so I told myself I was getting somewhere.

I wasn’t. Months of this, and I couldn’t point to one idea worth holding that the screen had actually handed me.

And here’s the part that took me years to admit. It wasn’t just me being a beginner.

When I started working in the markets professionally, everyone around me ran screens too. The junior analyst next to me. The PM. The most senior man on the floor, twenty years in, had his own filters he swore by. Different parameters, same ritual. Everyone was screening. Almost nobody was finding anything that way.

A couple of years back, I stopped.

Not because I found a better screen. Because I finally noticed where my good ideas were actually coming from, and it was never the screen. It was people. The investors I read. The ones I got on calls with, seasoned HNIs, operators who had been through three cycles, sometimes a junior analyst with one sharp observation. A writeup on Substack. A thread I couldn’t stop thinking about. Someone handing me not a ticker, but the question they were chasing.

That shift is the single best decision I have made as an investor. And it is exactly how I ran into the analysis I am about to show you.

I didn’t screen for it. I came across it: a video breaking down what the big four are doing with their AI spending, and it was the best take on the sector I'd seen in a long time. It stopped me cold.

Then it left me with one question.

Could I rebuild that myself? To that standard?

With Claude Code.

I know how that sounds. Most people in this business will tell you it can't be done, that serious research takes a data terminal, a team of analysts, and a budget none of us have. I'm not going to argue with them. I'm going to show you the whole thing instead, every prompt, every number, and the places I caught it getting things wrong. Don't take my word for any of it. Judge it for yourself.

This is the story of what happened when I tried.

What Claude Code Pulled First, and Why It Looks Like Madness

Here's the entire first pass in one clip, start to finish. I open the terminal inside Obsidian, paste in the prompt, and Claude Code goes out to the SEC filings on its own, pulls capex, operating cash flow and free cash flow for all four companies, and writes it all back into the vault. I handed it nothing. If you watch one thing in this piece, watch this.

I didn’t ask Claude Code for an opinion. I already had the video’s. I gave it the idea and pointed it at the source documents instead. The 10-Ks, the 10-Qs, the earnings releases. The filings, not a summary of them.

I never left Obsidian to do it. Claude Code runs right inside the vault, in a terminal you add from the community plugins in about a minute.

My whole research library sits on the left, Claude Code works on the right, and everything it finds gets saved back into the same place. Nothing scatters across tabs and tools.

Prompt 1: ok so I just watched this breakdown on the big tech names, Microsoft and Amazon mostly, and the whole thing is about how they're spending insane money on AI data centers right now and the market is basically punishing them for it. I want to check if that fear is actually real or if everyone's just overreacting, like is the market right to be scared here or not.
I haven't given you any filings, so you'll have to go get them yourself. pull the latest 10-Ks, the most recent 10-Qs, the earnings call transcripts, whatever you need, straight from the source, EDGAR or their investor relations pages. don't use some random article or summary, I want it from the actual filings.
first thing I want to understand is the spending. how much capex did Amazon and Microsoft actually spend last year, what are they guiding to for this year, and put Google and Meta next to them too so I can see the full picture across all four. give me the year over year jump in plain numbers.
then the part that actually matters, the cash. for Amazon show me operating cash flow vs capex and what's left as free cash flow, and what that does to the free cash flow margin. same for Microsoft. if there are analyst estimates anywhere for where free cash flow lands this year, pull those too, I want to see how bad people think it gets.
and don't just dump numbers on me. based on what's in the filings, tell me straight, is the market right to be this scared? and save whatever you pull into the vault so we don't lose it, I'm going to keep building on this.

The first thing it did was rebuild the spending picture from the filings. And the first number it handed back was the one that scares everyone.

Amazon spent about 77.7 billion dollars on net capex in 2024. In 2025 that jumped to 128.3 billion. A 65 percent increase in a single year. And on the latest earnings call, Jassy guided to roughly 200 billion for 2026. Microsoft ran the same play. Its capital spending went from 44.5 billion in fiscal 2024 to 64.6 billion in fiscal 2025, up 45 percent, and it has only accelerated since: the December 2025 quarter alone was roughly 37.5 billion, so even that fiscal 2025 number understates where the run rate sits today.

Then Claude Code pulled the cash, which is where it actually stings.

Amazon generated 139.5 billion in operating cash flow last year. It spent 128.3 billion of it on capex. What was left as free cash flow was 11.2 billion. The year before, that number was 38.2 billion. Free cash flow fell 71 percent in twelve months, and the share of operating cash flow Amazon got to keep dropped from 33 percent to 8 percent.

Read that cold, off the screen, and it looks like the biggest companies on earth setting fire to their own cash at the same time. That is exactly how the market read it. It is why the selloff happened.

And here is the trap. If you stopped reading the filings right here, you would sell too. Most people did.

But before I trusted a single one of those numbers, there was one step left. The one I never skip.

Rule One: I Never Trust the First Pass

The first output looked finished. Clean tables, sources listed, a confident take at the bottom. That polish is exactly when you should get suspicious.

So before I believed a single number, I made Claude Code audit its own work. Not re-read its notes, that’s worthless, it just nods along with itself. I sent it back to the actual filings, line by line, told it to recompute every number it had derived, and to assume it had gotten at least one thing wrong.

Prompt 2: ok before I trust any of this, go back and check your own work, and assume you got at least one thing wrong, because you usually do. don't just re-read your notes, that's pointless. go back to the actual filings you pulled from and re-confirm every raw number against the source, capex, operating cash flow, free cash flow, revenue, all of it, and tell me the exact line or page you got each one from.
then recompute everything you derived yourself, the year over year percentages, the free cash flow margins, the capex as a percent of revenue. don't trust the numbers you wrote down last time, redo the math from the base figures and see if it still matches.
and cross check against one outside source too, like the company's own release against an aggregator, and if they disagree tell me where and why, because sometimes it's just a definition thing like net vs gross capex.
then give me a clean list of what was right, what was wrong, and what you changed, and update the file so the corrected version is the one that stays in the vault.

It had. Two things, in fact. It had Microsoft’s fiscal 2025 revenue about 20 billion dollars too low, which had quietly thrown off the capex-intensity math built on top of it. And it had overstated Meta’s capex, because the first pass folded Meta’s finance-lease payments into the raw spending line.

These sound small. They are not. A wrong revenue number poisons every ratio sitting above it. And here is the one that would have actually embarrassed me: three of these four companies define free cash flow differently. Amazon nets out proceeds from asset sales. Microsoft and Alphabet don’t. Meta subtracts finance-lease payments on top of capex. Compare Meta’s free cash flow to Amazon’s without catching that, and you are quietly comparing two different things, then drawing a conclusion from a gap that doesn’t exist.

The first pass of any AI research will have errors. That is not the failure. The failure is trusting it. The discipline is the second pass, and a second pass that forces the model back to the source instead of letting it grade its own homework. That single step is the whole distance between research you can put your name on and the confident-sounding slop filling everyone’s feed.

Claude Code didn’t stop here. The next thing it pulled is what flipped the whole picture.

The Money Didn’t Burn. It Turned Into Assets.

So I went back and asked the other side of the question. If the cash is leaving, where is it going? I pointed Claude Code at the same filings, plus Amazon’s 2025 shareholder letter, to pull the part of the story the free cash flow panic leaves out.

Prompt 3: ok so the last numbers make these companies look like they're torching cash, but I don't buy that read and I want to test the other side. the whole point is capex isn't normal spending. when they buy data centers and chips they end up owning assets that earn for years, it's not gone like salaries or marketing.
first, go back into the same filings and show me the depreciation side. how much depreciation are they running now, how fast is it growing, and explain in plain terms how the capex they spend today turns into a depreciation hit over the next few years. I want to know what the real drag on reported profit actually is, because I think that's the only thing genuinely getting worse, and it's temporary next to how long these assets earn.
second, and this one matters most, pull from Amazon's own 2025 shareholder letter. Jassy talks about how the market reacted to AWS spending back around 2014 and how it played out. I want that parallel in their own words, the part about the spend and the long term and that "straight line was a lie" idea. keep any quotes short.
save it next to the capex file, and like before, don't trust your first pass, I'll verify after.

Here is what the screen doesn’t show you. When a company pays salaries or runs ads, the money is gone the moment it’s spent. When Amazon spends 128 billion dollars on data centers and chips, it does not vanish. It becomes 128 billion dollars of assets sitting on the balance sheet, earning for years.

The reason it looks like a wound is timing. Capex hits the cash flow statement all at once, today. But it reaches earnings slowly, spread out as depreciation over the life of the asset, four to six years for servers, far longer for the buildings. So the cash looks terrible now, while the earnings hit is still building.

And that hit is real. This is not a story where nothing is wrong. Depreciation is climbing fast. Microsoft’s depreciation and amortization jumped 53 percent in a single year, to 34 billion dollars. Amazon's total depreciation and amortization came to 65.8 billion for full-year 2025, up about 25 percent in a single year, and it keeps climbing as more of that capex lands on the income statement. Claude Code pulled the balance sheets to show why: Microsoft’s property and equipment grew by 69 billion dollars in one year, and Amazon’s AWS assets nearly doubled. All of that is only now starting to depreciate.

But here is the part that flips it. The worst of the drag is ahead, not behind, because capex is still growing, so depreciation keeps rising for two to three more years before it peaks. The fear that crushed these stocks was about the cash. The real cost is the depreciation. And depreciation is temporary next to how long the assets earn.

Amazon has run this exact movie before, and Jassy says so himself. In the 2025 letter he goes back to 2014, when AWS was deep in its own spending and a senior leader inside the company openly questioned why they were even in the business. The market disliked the spend then too. His point is that long-term bets never travel in a straight line, they zig up, stall, and double back. He borrows a phrase for it: “straight line was a lie.” Then the comparison that lands it. Three years after AWS launched, its revenue run rate was only in the tens of millions. Three years into the AI wave, Amazon says AWS’s AI run rate is already past 15 billion dollars, roughly 260 times larger at the same stage.

In 2006, as Amazon poured money into the infrastructure that became AWS, BusinessWeek ran a skeptical Bezos on its cover under the headline "Amazon's Risky Bet." A Piper Jaffray analyst caught Wall Street's mood: "I have yet to see how these investments are producing any profit." The spending was called a distraction. That distraction is now AWS. Bezos keeps the cover framed.

That is the whole reframe. The cash that looks burned is being converted into what Amazon believes is its next AWS-scale pillar, and the only genuine cost, depreciation, fades as the assets earn.

One honest caveat, because it’s the hinge the whole thing turns on. This holds only if the AI revenue actually shows up. If demand disappoints, that rising depreciation stops being temporary and becomes a years-long drag with nothing behind it. So the question is no longer “why are they burning cash.” It is 'when do these assets start paying, and is the demand really there.' But before I let any of that into the thesis, I ran it through the same check as the first set of numbers.

Read more

For the past couple of months, I have been writing about Claude Code for investment research, and the reaction split almost perfectly in two.

The people who actually tried it became serious fans. They got past the black terminal and realised the funny part: you do not need to be a developer to use it. You can talk to it in plain English, point it at your annual reports, your transcripts, your messy folder of consultancy PDFs, and it starts working like a research analyst sitting inside your laptop.

Most people never crossed that first barrier. They saw the terminal and quietly checked out, and I understand exactly why. Finance professionals did not spend years learning valuation, earnings power and management behaviour just to feel stupid in front of a blinking cursor. Humanity has invented many forms of unnecessary pain, and command-line anxiety is apparently one of them.

So today I want to step one layer simpler. Not away from Claude Code, because I still believe the CLI tools are where serious AI research eventually goes. But before most investors get there, they need something easier to hold.

That brings us to Claude Skills.

I started building Skills very early, right after Anthropic shipped them, and for three or four months I was obsessed. I built finance skills, broke them, rebuilt them, debugged prompts for hours, and tried to turn every repeatable piece of my research into a reusable system. It felt like real progress. The outputs looked the part, clean and structured, the kind of thing you screenshot and post.

And then something happened that I did not notice for weeks. I stopped opening them.

Nothing broke. The equity research skill still ran, the 13F screen still produced a tidy output, I just drifted away from my own work without realising it, until one day I sat with the uncomfortable question of why. The honest answer was that not one of those skills had ever changed a decision I actually made. The output was beautiful and my conviction sat exactly where it would have been without any of it. I had built a very sophisticated way of feeling like a more serious analyst.

Claude Skills are useful. But they are not the end goal.

Most people are approaching them completely wrong. They download somebody else’s investment Skill because it looks sophisticated from the outside, maybe it says Buffett-style investing or 13F framework or equity research copilot, they use it for a week, the outputs look impressive, and then they quietly stop, because the Skill never actually helped them build conviction.

That is the real problem, and it runs deeper than tooling. Investment research is deeply personal. Two successful investors can agree on eighty percent of the principles and still work completely differently, because the way they extract information, the way they connect dots, the questions they keep asking and the things they choose to ignore are never the same. You cannot inherit that from a zip file.

So this post is not a download-this-and-you-are-done tutorial. I am going to build a real investment research Skill in front of you, show you the structure, the output and the mistakes I made, but the bigger point is the one underneath it. A skill will not make you a better investor. What it can do, if you build it yourself, is force your own thinking into the open, the questions you always ask, the ones you forget, and the gaps you have been quietly walking around for years.

So here is the question I would sit with if I were you. That skill you installed last week, the equity research copilot, the Buffett framework, the 13F tracker someone handed you in a zip file. Be honest. Has it changed a single decision you have made? Or does it just make you feel like the kind of analyst who uses tools like that?

What Actually Happens After You Build Investment Skills For 90 Days

I assumed the hard part of all this would be the prompt engineering. It was not.

The hard part was how honest it forced me to be about my own research. One day I would care deeply about management commentary. The next I would lose three hours inside capital allocation. Some weeks I obsessed over industry structure, other weeks I skipped it entirely and spent all my attention on whether earnings could actually last. I had always told myself I had a process. The moment I tried to turn it into reusable instructions, I ran straight into how much of it was not a process at all.

That is what building a skill does, and it does it brutally. You see which questions you ask every single time, which ones you forget, which parts of your workflow are real signal, and which parts are just there to make you feel sophisticated while adding almost nothing to conviction.

That was the point where skills finally became useful to me. Not because they automated research, they cannot, but because building them forced me to be honest about which parts of my process were actually repeatable and worth keeping. And once I saw that, I stopped trying to build one giant equity research brain and started building small skills around the specific moments where consistency actually matters. That worked far better.

You can see this the moment two people build the same skill. Hand the same earnings-review brief to a margins-obsessed analyst and a management-quality analyst and you get two different tools. One builds it to interrogate the cost line and operating leverage. The other builds it to track what management promised last quarter against what they delivered this one. Same name on the folder, completely different instructions inside.

So before I write a single line of a SKILL.md file, before I touch folder structure or decide whether the output is a memo or a checklist, I force myself through four questions.

The Four Questions I Answer Before I Build Anything

This sounds basic, but it is where almost every skill goes wrong. Equity research is too broad. Investment research is too broad. Even analyse a company is too broad. None of those are workflows. They are ambitions, and a skill built on an ambition will try to do everything and end up doing nothing you actually trust.

A useful skill sits inside one specific moment of your process. Reviewing an earnings call the morning after results. Comparing management commentary across four quarters. Checking whether capital allocation has quietly drifted over five years. Turning a 10-K into a list of open questions. Reading expert call notes and pulling out the things that could break the thesis. Once the moment is that narrow, the skill no longer has to pretend it can replace you. It only has to do one repeated thing well, every time.

This is also where most downloaded skills fall apart. They try to be a full analyst, because a full analyst sounds impressive in a product description. But in real research the leverage almost never comes from replacing the whole process. It comes from making one repeated step sharper and more consistent than you manage on your own.

So for this post I am not going to build a complete equity research analyst. It would look impressive and it would be useless by the third run. I am going to build something deliberately narrow. A thesis-breaker.

The job of this skill is simple. You give it your thesis, along with whatever you have collected, the notes, the filings, the transcripts, and it goes looking for what could break it. It does not tell you to buy or sell. It does not pretend to know the future. It forces your own assumptions into the open and asks the questions you are most tempted to skip, the ones where the answer might cost you the position. Whether the earnings assumptions are too clean. Whether management commentary has quietly changed. Whether the valuation already prices in the good news. Whether the entire thesis is leaning on one variable behaving perfectly.

That is where AI actually helps a serious investor. Not by becoming Buffett in a zip file. By becoming a consistent sparring partner around one specific moment that matters.

Once the moment is clear, the next decision is not what the skill should do. It is what it should never do. This matters more in investment research than almost anywhere else, because AI gets confident far too quickly. Ask it to sound intelligent and it will. Ask it to analyse a company and it will hand you a clean, polished answer even when the evidence underneath is thin, stale or missing. A beautiful memo built on weak evidence is still weak research. It just looks more respectable while it misleads you.

So before I write the workflow, I write the boundaries. For the thesis-breaker they are simple. It does not give buy, sell or hold calls. It does not pretend missing data does not matter. It does not invent numbers, peer comparisons, management quotes or valuation assumptions. And it does not attack the thesis just to sound contrarian, because that failure is as useless as flattery. A thesis-breaker that lists every possible risk in the world looks analytical and says nothing.

A good one separates the risks that actually threaten the thesis from background noise. If the thesis depends on margin expansion, it goes after what breaks margins. If it depends on operating leverage, it tests whether revenue growth is really enough to carry the fixed cost base. If it depends on management, it compares what they said before with what they are doing now. The guardrails are not compliance decoration. They are what stops the skill from quietly turning into a confident generalist. The single rule underneath all of them: the output should make me think harder, never make the decision for me.

I do not want the input to be clean, because real research never is. Sometimes you have a half-written thesis. Sometimes a page of notes from a call. Sometimes a valuation assumption sitting in your head that you have never actually written down. A useful skill has to take that messy material, work out what it has and what it is missing, and still separate the core thesis from the noise.

So the input is flexible but not lazy. At a minimum it asks for the company, the current thesis, whatever source material exists, and the specific part of the thesis you want pressure-tested. If something is missing, the skill does not paper over it. It says what it has, what it does not, and which parts of the analysis will be weaker as a result. That one choice matters more than it looks. A research skill should never reward messy thinking with a clean answer. Give it two lines of thesis and it should tell you the read is preliminary. Give it no numbers and it should not invent any.

I do not want a long memo just because long memos feel serious. The output has to be short enough to read in the middle of an actual research session and sharp enough to change what I do next. For the thesis-breaker, it returns five things: my thesis in plain English, the assumptions hiding inside it, the strongest objections to it, the evidence I am still missing, and the questions I should answer before I add to the position.

That is the full design. A narrow moment, clear boundaries, realistic inputs, a useful output. Now I can stop describing the skill and actually build it.

Building the Thesis-Breaker

Now that the design is clear, I can turn it into something real. And the first decision is the one most people get wrong.

For the first version, I am keeping this deliberately simple. One folder. One SKILL.md file. That is it.

This matters because people often make Skills look more complicated than they need to be. They create multiple files, nested folders, examples, checklists, and instruction documents before the Skill has even proved that it is useful. That may look serious, but it is not always efficient.

The file tells Claude when to use the skill, what workflow to follow, what to produce, and what it must never do. If the same instructions are going to run every time, they can simply live in that one file. I would only split it later, and only if the skill earns it. If the workflow grows too large, the methodology can move into its own file. If the guardrails get detailed, they can move into another. If I start adding worked examples across sectors, those get a folder. But none of that on day one. A multi-file skill is not automatically more advanced. It is only better if the extra files genuinely reduce confusion, and on the first run they never do. They just hide the fact that you have not tested anything yet.

The goal is not the most impressive skill folder. It is the simplest version that actually works, fast enough that you can point it at a real thesis today.

Here is the prompt I would give Claude or Claude Code to build the first version.

The rest of this issue is for members. What follows is the part I can’t fake for you: the skill run live on a real Alphabet thesis, where it broke, and what it told me to build next. I opened Alpha with AI to paid members three days ago. For the next stretch, until 8 June, the first year is 25% off, my thank-you to the people who showed up before there was ever a wall.

Claim 25% off →

Read more

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 rhyt…

Read more

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 research piece on the semiconductor capex cycle. You read it. It’s good. You make a mental note that this’ll matter for the chip names on your watchlist.

Friday rolls around. You’re researching one of those names. You remember the article. You don’t remember where you saw it. You scroll X for ten minutes. You search your bookmarks. You give up. You do the analysis without it.

Multiply that by six months of reading. That’s the real bottleneck in AI-powered research. Not the AI. The collection.

Every analyst I know has tried to build a personal research library. Most have failed. The reason isn’t laziness. It’s that the act of filing is exhausting. Bookmark the page. Open a folder. Rename the file. Pick a tag. Upload it somewhere. Six months later, find it again. The first time you do it, it takes ninety seconds. The fifth time you do it that morning, you stop doing it.

The AI tools we’ve been talking about in this series, Claude Code, NotebookLM, the rest of the stack, all assume you’ve solved this problem. They assume the right document is already in the folder when you ask the question. They don’t help you put it there.

That’s the gap.

Now picture the same Monday. You read the same article. You hit one button in your browser. The article is already a markdown file in your research folder. You didn’t pick a name. You didn’t pick a tag. You didn’t decide where it goes. Friday comes. You ask Claude Code: what have I read on this sector recently? It pulls the article. It pulls the concall transcript you clipped three weeks ago. It pulls the chart you saved last month.

Now zoom out. Six months. A year. Two years.

Every article you’ve ever read. Every concall. Every chart. Every newsletter. Every X thread. All in one folder, all in markdown, all readable by Claude Code in a single query.

Your research stops disappearing. It starts compounding.

That’s what Obsidian does. The next sections are about how.

2. Obsidian, In One Paragraph

Obsidian is a free app. You download it. It points at a folder on your computer. Every note you create is a plain text file inside that folder, written in markdown. The folder is the product.

That sounds boring until you realize what it means. Markdown is the format AI models read most easily. Plain text on disk is the format Claude Code can write to, edit, and search without any bridge or API. A folder of markdown files is, by default, the most AI-friendly research library you can build. Obsidian’s only job is to make that folder pleasant to live in: a sidebar, a search bar, a graph view of how your notes connect, a plugin system for the things the core app doesn’t do.

If you read Part 2 of this series, you’ve already installed it. You created a vault with three folders, raw/, wiki/, and output/, plus a CLAUDE.md rulebook that tells Claude Code how to behave inside it. If you haven’t done that setup yet, do it now, 10 minutes of work, and the rest of this newsletter assumes it’s in place.

Prefer to watch? I recorded a forty-three-minute walkthrough of the entire system, including live use cases and the parts that are hard to show in writing. The newsletter stands alone, but the video shows what the screen looks like.

What I want to spend the rest of this piece on is what happens after the install. Because Obsidian by itself is just a note-taking app. Obsidian wired into Claude Code, with one browser extension and one design principle, is the part doing the quiet work in the background.

The browser extension is called Web Clipper. The design principle is that you don’t decide where anything goes. You’ll see what I mean.

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 someone had handed me on day one. By the end of it, you’ll have Claude Code installed, a knowledge base that compounds every piece of research you do, and three tools bolted on that let Claude Code reach into the live web, drive a browser, and query your own notebooks.

If you’ve watched the video that goes with this, you’ll know the shape of it. The newsletter goes deeper on the prompts, the file structure, and the rules that make the whole thing work.

Let’s start with the one idea that changed how I think about all of this.

Claude vs. Claude Code: The One Thing Nobody Explains

Claude and ChatGPT are chatbots. You ask, they answer. You ask again, they answer again. Useful, but limited. The conversation is the product.

Claude Code is different. Claude Code is Claude with hands.

Think about what happens when you ask ChatGPT to help with an investment research workflow. You can ask it to screen for a few stocks. You can paste in financials and ask for a DCF. You can give it a draft and ask it to clean up the language. But each of those is one step, with you in the middle, copying and pasting between the chat and the rest of your work.

Now picture a real research workflow. You screen the universe. You shortlist on a few parameters. You apply your firm’s internal framework to the shortlist. You pick two names. You pull financial statements for both. You build a model. You stress test the model. You arrive at an intrinsic value. You draft an equity research report. A senior analyst reviews it. You publish.

A chatbot can help with one step at a time. Claude Code can run the whole chain.

You give it the end goal. It opens a browser if it needs to. It scrapes data if it needs to. It writes files. It reads files. It runs five things in parallel if the task allows. It asks you for input only when it actually needs you. The work happens while you do something else.

That’s what “hands” means. ChatGPT is a brain you talk to. Claude Code is a brain that runs your workflows.

There’s a line I keep coming back to. A smart, hardworking person does more by doing more. A wise person does more by eliminating more. Claude Code is the eliminator. Most of what we call “research work” is actually data gathering, formatting, copying, pasting, switching tabs. Claude Code takes that off your plate so the only thing left is the part that actually requires you.

That is the unlock. Everything else in this newsletter is just how to set it up.

Step One: Install Claude Code (The Easy Part)

If you'd rather watch this whole setup happen on screen, including the Playwright and Firecrawl install in the next section, I recorded a 16-minute walkthrough that covers everything end to end:

Go to the Claude Code page on Anthropic’s site. You’ll see two install commands, one for Mac and one for Windows. Copy the one for your machine.

• Official Claude Code setup docs: https://code.claude.com/docs/en/quickstart

If you’re on a Mac, open Terminal. If you’re on Windows, open PowerShell. Paste the command, hit enter, wait a minute. That’s the install.

Now type claude and hit enter. The Claude Code prompt opens. You can start typing in plain English. Ask it anything. “Hi, I’m new here, how should I get started?” works fine. It will tell you.

That’s it. That’s the install.

There’s one more thing to do before you go further: download Cursor.

• Official Cursor Page: https://cursor.com/home

Cursor isn’t an alternative to the terminal. It’s where the rest of this system lives. When you set up the Obsidian knowledge base in the next section, you’ll open your Obsidian vault as a folder inside Cursor. Your raw, wiki, and output folders sit in the sidebar. Claude Code runs in a panel next to them. You can watch files get created, edited, and indexed in real time, in the same window. Everything you build from here on out happens in this one place.

You can still use the plain terminal if you want to. I sometimes do, especially when I want to watch Claude Code grind through something complex. But Cursor is where the daily work actually happens, because it’s the only place where the knowledge base, the chat, and the tools are all visible at the same time.

Claude Code on its own is useful, but it’s not what makes the system in this newsletter work. The install is two minutes. The setup that actually changes your research is what comes next.

Optional, only if you don’t want a Claude subscription

One quick note before we move on. Everything from here assumes you have a Claude subscription, Pro or Max. If you don't, and you don't want to buy one just to experiment, there's a working alternative called MiniMax M2 that slots into Claude Code as a replacement engine at roughly seven percent of the cost. I wrote a full setup guide for it in this piece I Quit Claude Code Twenty Times. Now It Reads Every Annual Report I Own. Set it up using that guide, then come back and pick up from the next section. Everything that follows works identically.

Step Two: Set Up Obsidian as Claude Code’s Memory

Claude Code on its own has no memory. Every session starts fresh. You can have a brilliant conversation with it on Monday, close the terminal, and on Tuesday it remembers nothing. For most coding tasks that’s fine. For research, it’s a problem. Research compounds. The note you took on a semiconductor company in March should be findable in November, alongside everything you’ve learned about the sector since.

This is what Obsidian solves. Obsidian is a free app that turns a folder on your computer into a personal research library. Each note is a plain text file. You can link notes to each other, organize them into topic folders, and search across the whole library instantly. There’s no database, no cloud, no lock-in. Your research lives on your machine, in files you can read with any text editor.

The trick is that Claude Code can read and write to that same folder. Once you set it up correctly, Obsidian becomes Claude Code’s long-term memory. You hand Claude Code the role of librarian. It files what you collect, summarizes what you read, links related ideas across topics, and pulls from the library every time you ask a question. Over time the library gets smarter, because every answer Claude Code gives you gets filed back into it.

Here’s how to build it.

Install Obsidian and create your vault

Download Obsidian from obsidian.md. It’s free for personal use, and works on Mac, Windows, and Linux.

Open Obsidian and click “Create new vault.” A vault is just a folder on your computer where Obsidian stores your notes. Name it whatever you want (mine is called Vault itself). Pick a location you’ll remember, somewhere in your Documents folder works fine. Obsidian will open the empty vault.

Now open that same vault folder inside Cursor. File → Open Folder → select your vault. You should see the folder name appear in Cursor’s sidebar, empty for now. This is where everything happens from here on.

Create the folder structure

Open Claude Code inside Cursor (the sidebar panel, or the terminal, your choice). Paste this prompt exactly:

Create this folder structure for my knowledge base:

- raw/ — this is my inbox where I'll dump source material
- wiki/ — this is your domain, you'll write and maintain everything here
  - Create a _master-index.md inside wiki/ with the heading "Knowledge Base Index"
    and a note that says "Topics will be listed here as they are created."
- output/ — this is where query results and reports go

Just create the folders and that one file. Nothing else yet.

Claude Code will create three folders and one file. Open Obsidian and you’ll see them in the sidebar. That’s your skeleton.

Three folders, three jobs. raw/ is your inbox where you dump anything you want the system to learn from: articles, transcripts, screenshots, notes. wiki/ is the librarian’s domain, where Claude Code writes structured summaries, organizes them into topic folders, and maintains a master index of everything. output/ is where finished work lands: research reports, query answers, analyses you want to keep separate from the library itself.

The rulebook (CLAUDE.md)

This is the most important file in the whole system. CLAUDE.md is the rulebook Claude Code reads every time you open it inside this vault. You write the rules once, and Claude Code follows them forever. Without this file, Claude Code is just a clever assistant. With it, Claude Code is a disciplined librarian.

Create a file called CLAUDE.md in the root of your vault (not inside any of the three folders, but next to them). Paste this in:

This file tells you how to maintain this knowledge base across every session.

## Knowledge Base Rules

- This is an LLM-maintained knowledge base. You are the librarian.
- The wiki/ folder is YOUR domain — you write and maintain everything in it.
  I rarely edit wiki files directly.
- raw/ is the inbox. When I dump files here, you process them into the wiki
  during a "compile" step.
- wiki/_master-index.md is the entry point. It lists every topic folder with
  a one-line description. Always keep this up to date.
- Each topic gets its own subfolder in wiki/ (e.g., wiki/ai-agents/) with its
  own _index.md that lists all articles in that topic with brief descriptions.
- Always use [[wiki links]] to connect related concepts across topics.
- When compiling raw material:
  1. Read the raw file
  2. Decide which topic it belongs to (or create a new one)
  3. Write a wiki article with key takeaways and relevant links
  4. Update that topic's _index.md
  5. Update wiki/_master-index.md
  6. If a raw file spans multiple topics, create articles in both and cross-link
- Keep articles concise — bullet points over paragraphs.
- Include a ## Key Takeaways section in every wiki article.
- output/ is for query results and generated reports.
- When answering questions, read _master-index.md first to navigate, then
  drill into the relevant topic _index.md, then read specific articles.
- When I ask you to "compile", process everything in raw/ that hasn't been
  compiled yet into the wiki.
- When I ask you to "audit" or "lint", review the wiki for inconsistencies,
  broken links, gaps, and suggest improvements.

Save the file. From now on, every session starts with Claude Code reading this rulebook.

The daily input: Web Clipper

Web Clipper Page: obsidian.md/clipper

You need a way to get articles into your raw/ folder without copying and pasting. Install the Obsidian Web Clipper extension on your browser (Chrome, Brave, Edge, Firefox all supported).

Open the Web Clipper settings. Add your vault. Then go to Templates and edit the Default template:

• Vault: select your vault

• Note location: raw

• Note name: {{date|date:"YYYY-MM-DD"}}-{{title|safe_name}}

Now any article you read on the web becomes a clean markdown file in your inbox with one click. An earnings transcript, an FT piece, a 10-K excerpt, a Substack post, all get clipped the same way.

One optional add-on: install the Local Images Plus plugin inside Obsidian (Settings → Community Plugins → Browse → search “Local Images Plus”). When you open a clipped note, this plugin downloads every image from the article into your vault, so your library stays intact even if the original page goes down.

The daily workflow: four verbs

Once everything is set up, the workflow is four verbs.

Clip. You see something worth keeping. One click in your browser, it lands in raw/. You don’t decide where it goes, you don’t write a summary, you just clip it.

Compile. Once a week, or whenever your inbox feels full, open Claude Code and type:

Compile everything in raw/ into the wiki. For each file:
1. Read it and identify the core topic
2. Create or find the right topic folder in wiki/
3. Write a wiki article with a summary, key takeaways, and [[wiki links]]
   to any related concepts
4. Update the topic's _index.md
5. Update wiki/_master-index.md

Cross-link between topics wherever relevant.

Claude Code reads each clipped article, decides which topic it belongs to, writes a structured summary note, files it in the right folder, and updates the indexes. By the time you finish your coffee, your inbox is empty and your library is bigger.

Query. Ask the library questions. Simple ones: “What were the key findings from the Bain semiconductor report I clipped last month?” Cross-referencing ones: “How does the slowdown in Chinese auto exports relate to what I’ve been reading about commodity demand?” Synthesis ones that file the answer back into the library: “Based on everything in the wiki, what are the main bull and bear cases on Indian specialty chemicals? Save your answer as a new wiki article and link it to the sources you referenced.”

That last query is the move that makes the system compound. Every question you ask becomes a new note. Every note links to its sources. The library grows smarter every time you use it.

Audit. Once a month, type: “Audit the wiki. Look for inconsistencies, broken links, missing cross-references, and gaps in coverage. Don’t make changes yet, just give me a report.” Claude Code walks the whole library and tells you where it’s getting fuzzy. You decide what to fix.

That’s the system. Inbox, librarian, library, output. Four folders, one rulebook, four verbs.

The reason this matters more than it looks: the system is the discipline. Anyone can install Obsidian and Claude Code. The reason your research compounds instead of leaking is that the rulebook forces consistency. Every clip gets filed the same way. Every summary follows the same format. Every query has access to everything you’ve ever read. After sixty days of running this, I can ask Claude Code “what have I learned about position sizing this quarter” and get a real answer in under a minute, drawn from articles I’d half-forgotten clipping.

Now we add the parts that let Claude Code reach beyond your library, into the live web.

Step Three: Give Claude Code Hands on the Web (Playwright + Firecrawl)

The knowledge base you just built is powerful, but it’s also closed. It only knows what you’ve fed into it. For real research work, you need Claude Code to reach out into the live web: pull a balance sheet from a screener, scrape an investor relations page, search for the latest filings on a company you’re tracking. That’s what these next two tools do.

Playwright lets Claude Code drive a real browser. Firecrawl lets Claude Code search and scrape the web at scale. Both are free and open source. Both install in about two minutes. Together they’re the difference between a librarian who only reads what you bring home and a librarian who can also walk to the library across town and bring back what you need.

Playwright: the browser

Playwright is a browser automation tool from Microsoft. Once it’s installed, Claude Code can open a browser, navigate to any page, click buttons, fill forms, log into accounts, and read what’s on the screen, all without you touching the mouse.

For finance work, this matters in places where the data lives behind interaction. A screener that requires you to set ten filters before showing results. An investor relations page that hides quarterly numbers behind a dropdown. A regulator’s portal that needs you to accept a disclaimer before downloading a filing. Anywhere a regular scraper would fail because the page expects a human, Playwright lets Claude Code be that human.

To install it, open Claude Code in your vault and paste:

I want to install Playwright CLI from Microsoft so you can drive a browser
on my behalf. The repository is at https://github.com/microsoft/playwright-cli.
Walk me through the installation step by step for my [Mac / Windows] machine,
beginner-friendly, and run the commands you need to run.

Claude Code will install it, walk you through any prompts, and confirm when it’s ready. Test it by asking something simple: “Open a browser, go to screener.in, and tell me what’s on the homepage.” If Playwright is installed correctly, a browser window opens, navigates to the page, and Claude Code reports back what it sees.

Firecrawl: the web scraper

Firecrawl does something different. Where Playwright is a hands-on browser, Firecrawl is a fast, programmatic way to pull clean text from any web page or run a web search and pull text from the top results. It converts whatever it finds into clean markdown files that Claude Code can read directly.

The use case finance people will recognize immediately: you want to pull insider trading data from Finviz for the last two weeks. You want to scrape an annual report from a company’s IR page. You want to search for “latest news on Indian specialty chemicals” and pull the top ten articles into your knowledge base. Firecrawl does all three with a single command each.

To install:

I want to install Firecrawl CLI so you can search and scrape the web on my behalf.
The official docs are at https://docs.firecrawl.dev/sdks/cli.
Walk me through the installation step by step for my [Mac / Windows] machine,
beginner-friendly, and give me every command I need to run.

Once installed, Firecrawl becomes a tool Claude Code can call directly from the terminal. You don't have to invoke it manually each time. When a task requires the live web, Claude Code recognizes it has Firecrawl available and uses it automatically.

What this looks like in practice

Here’s a real prompt I ran last week. The setup: I wanted to deploy capital across five names and only had two on my shortlist. I needed three more.

I'm screening for names to deploy capital. Go to finviz.com, pull insider
trading data for the last two weeks of US-listed companies. Analyze the
data for strong buy signals. Give me a top 10 watchlist with reasoning for each name.
Also flag red flags and names to avoid.

Claude Code asked permission to use Firecrawl. I said yes. It went to Finviz, pulled the data, parsed it, ran the buy-signal logic, cross-checked fundamentals, and came back with a ranked list of ten names. Each one had a thesis, a list of insider purchases (with who bought, when, and how much), key risks, and a summary scorecard. Three minutes start to finish.

If I’d done that manually, it would have been 90 minutes minimum, and I’d have introduced errors copying data between Finviz and Excel. Claude Code did it without leaving the terminal.

One thing about permissions

Every time Claude Code wants to use a tool like Firecrawl or Playwright, or modify a file, or run a command, it asks for permission. By default, this means a yes/no prompt every few steps. Useful when you’re learning. Annoying once you trust the system.

There’s a flag called --dangerously-skip-permissions that turns the prompts off entirely. Claude Code can then run any tool, modify any file in your vault, and execute commands without checking with you each time. The name sounds alarming, and it should. You’re handing Claude Code full access to your working directory.

I’ve been running with this flag on for sixty days. Nothing has broken. No file deleted by accident, no command run that shouldn’t have been run, no security issue. What changed is that I stopped sitting in front of the terminal waiting to click “yes.” I started giving Claude Code a task and walking away. By the time I came back with coffee, the task was done.

The reason this works is the rulebook. CLAUDE.md tells Claude Code exactly what its job is and what the boundaries are. Combined with the fact that Claude Code only has access to the vault folder you opened, not your whole machine, the risk is much smaller than the name of the flag suggests. I’d recommend running with permissions on for the first week so you can see what Claude Code is doing. Once you trust the pattern, turn permissions off and let it work.

That’s a personal call. Some readers will keep permissions on forever and that’s fine. The system works either way.

What 60 Days Has Taught Me

The setup above takes about an hour. The system it creates is something I’m still learning to use sixty days in.

A few things have surprised me.

The first is how quickly the terminal stopped feeling like a coding tool. By the end of the first week, I was typing into Claude Code the same way I type into ChatGPT. Plain English, no commands, no syntax. The intimidation factor people warn about is real for the first day, and gone by the third. If you’re a finance person reading this and hesitating, you’re hesitating about a problem that won’t survive the first session.

The second is what happens when you stop being a chatbot user and start being a workflow operator. The shift is subtle but everything downstream changes. You stop asking Claude Code to “help you” with one task and start handing it the whole task. Screen these names, run them through this framework, pull financials for the survivors, build models, draft a one-pager on each. You give it the end goal and walk away. The work happens in the background. You come back to a folder of finished output.

The third is how much research used to leak. Before this system, I had research scattered across Notion, Apple Notes, browser bookmarks, downloaded PDFs in five different folders, and a Substack drafts folder I rarely opened. I’d rediscover the same insight twice, sometimes three times. The Obsidian knowledge base ended that. Everything I read now lands in one place, gets filed by Claude Code into the right topic, and gets pulled back when I ask a related question six weeks later. Nothing leaks. Information compounds.

One more tool worth knowing about: NotebookLM. It’s Google’s hosted research tool, and it solves a different problem than Obsidian. Obsidian is your library. NotebookLM is a focused workspace for one specific research target: a single company, a single sector, a batch of filings. You upload the sources, and NotebookLM gives you grounded, cited answers across just those documents. There’s a Python wrapper that lets you query a notebook directly from inside Claude Code, which means you can build a workflow where Claude Code pulls from your Obsidian library and a focused NotebookLM source set in the same prompt. I wrote about NotebookLM and the workflow it unlocked for me here: “I quit Claude Code twenty times”. Worth reading if you do company-specific or sector-specific research.

What’s coming next

This newsletter is part of a series. Now that the setup is done, the next pieces will go deep into specific finance workflows: a full equity research workflow that runs end to end inside Claude Code, a wealth management workflow for prioritizing client calls after a market event, a monthly accounting audit workflow, and a portfolio monitoring system that runs on a virtual server and pings you when something needs attention. Each of these will use the system you just built.

If you want the rest of the series as it comes out, you’re already in the right place by reading this.

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, it’s the most powerful research tool you can have on your machine right now. The hour you spend setting this up is the hour your research stops leaking and starts compounding.

That’s the whole thing.

If you want the full workflow as a clean download, PDF setup guide, the prompts and CLAUDE.md as separate files, and the companion video, the resource card is on shikshannivesh.com. Same content, easier to keep on your desk.

The launch offer

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 →

🧰 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 all live in one place: 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.

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.

Claim 25% off →

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, started, restarted, abandoned.

The only book I have actually finished in the last twelve months is Jim Collins’ Good to Great. Even that took me four months of stolen evenings, weekend mornings, and one long flight. By the time I got to the last chapter I had forgotten the framework from the first one.

Here is the part I never said out loud until now. I read more in a typical week on Substack than I read in a year in books. Not because Substack writers are smarter than Dalio or Marks or Klarman. They most probably are not. But Substack gives me something the books cannot give me, which is live perspective. Recent context. The AI angle. Applied thinking. The exact stock I was researching yesterday, analyzed by someone who is also researching it today.

The books sit on the shelf and lose. Every time.

Yet I know, and you know, that the frameworks inside those books would change how we research. Dalio’s Big Cycle is not abstract macro theory. It is an operating system for understanding where any country, any sector, any asset sits in a much larger story. Marks on cycles. Klarman on margin of safety. Collins on what separates good companies from great ones. These are not just ideas. They are lenses. Lenses change what you see.

The lie I have been telling myself for years is that one day I will have time. I will take a sabbatical. I will go through all of them properly. I will emerge with a notebook full of frameworks and finally start applying them.

That day is never coming. You know it. I know it.

Last month, on the eleventh rewatch of the Big Cycle video, something different happened. Not because the video got shorter. Not because Dalio suddenly got simpler. The video is still 40 minutes long and the framework is still vast.

What changed was a different question.

What if I did not need to finish the book? What if I did not even need to start it? What if the framework itself could go where I actually work, into the Claude project where I research stocks?

That question turned into a build. That build turned into a skill, a Claude Skill that lives in my Equity Research project alongside the Kill Report and the Industry Playbook. It runs Dalio’s Big Cycle lens on any stock, sector, or country I throw at it. It does not write the model for me. It does not pretend to know what to buy. It does one thing: it makes sure that before I commit to a thesis, the macro view I always meant to integrate is actually integrated.

That is what this edition is about.

Not Dalio. Not the book. Not even the skill, really.

The thing underneath all of it is a way to take any author whose frameworks have been sitting on your shelf, whether it is Dalio, Marks, Damodaran, Klarman, Collins, or whoever, and bring their thinking into your workflow without ever finishing the book.

I will walk you through exactly how I built it. Every prompt. Every step. The SKILL.md file is at the bottom of this edition, ready to install. The companion PDF guide is on the website if you would rather read it that way.

By the end of this newsletter you will have done two things.

One, you will have a working Big Cycle Skill installed in your Claude project, ready to run on any stock you research.

Two, you will have a method, a four-step build pattern that works for any book, any framework, any author. The next time you find yourself watching a video for the eleventh time, you will know what to do with it.

Let us start where every good build starts. Not with the book. With the question the book is supposed to answer.

The Pattern Break

For years my reading problem felt like a time problem. If I just had more time, I would finish the books. If I just had a quieter month, I would get through Principles. If I just had a long flight, I would knock out Big Debt Crises.

It was never a time problem.

It was a workflow problem.

The frameworks in those books are not designed to be remembered. They are designed to be applied. Dalio’s Big Cycle is not something you internalize by reading it once. It is something you run, every time you look at a country, a sector, or a stock. Marks on cycles is not a concept you absorb. It is a question you ask, every time you build a thesis. Klarman on margin of safety is not a chapter. It is a check, on every position you size.

Books deliver these frameworks in the wrong format for how I actually work. They deliver them as prose. I need them as prompts.

That was the realization on the eleventh rewatch.

Dalio had already done the hard part. The Big Cycle framework is fully formed. It has explicit determinants. It has stages. It has if-then logic about what happens to currencies when debt gets too high, what happens to internal order when wealth gaps widen, what happens to empires at the peak of their cycle. It is, structurally, already a skill. It is just stuck inside a 40-minute video and a 600-page book.

What I needed was a way to lift it out.

Not summarize it. Not write a Substack note about it. Lift the actual operating logic out of Dalio’s words and drop it into my Claude project as a working skill. The same way I had already done with the Kill Report. The same way I had already done with the Industry Playbook. Skills that sit in the project, wait to be called, and run the same check the same way every time, on whatever stock I am researching.

The shift in my head was small but it changed everything.

I stopped thinking of the books as things I had to read. I started thinking of them as raw material I had to extract. The author had done the thinking. My job was not to sit through the thinking again. My job was to convert it into a tool I could use tomorrow.

That reframe is the whole game. Once you see the books as source material instead of as obligations, the entire reading problem dissolves. You do not need to finish the book to use the framework. You need to extract the framework cleanly, build it into a skill, and let the skill carry the author’s logic into your workflow forever.

By the time I closed the YouTube tab that night, I had stopped feeling guilty about the unread shelf. I was looking at it differently. Five books on that shelf. Five frameworks waiting to be lifted. Five skills that could live in my Equity Research project by the end of the month.

I started with Dalio. Big Cycle first. Because if you are an equity research analyst doing bottom-up work, the macro lens is the one most likely to be missing from your workflow, sitting in a separate browser tab, never quite making it into the actual research.

The next four sections are exactly what I did. Step by step. Prompt by prompt. The Big Cycle Skill is the demonstration. The method works for any book on your shelf.

The Build, In Four Moves

The build itself is small. Four moves, maybe two hours, most of which is Claude doing the work while I drink coffee.

The moves are these. Decide what the skill is for. Get the source material into the project. Extract the operating logic. Write the SKILL.md and install it.

Move One. Decide what the skill is for.

Before I went near the video, I forced myself to write one sentence. Who is this skill for, what situation is it for, what does it produce.

For me the sentence came out like this. An equity research analyst, researching a stock with material exposure to a specific country, who needs Dalio’s Big Cycle framework to run on that country and/or sector with material exposure to a that country before they commit to the thesis.

That sentence is the whole filter. It told me the skill is country-level, not stock-level. It told me the skill runs upstream of the model, not inside it. It told me the output is a regime read and a set of pressure questions, not a price target. Once that sentence existed, every later decision was easy.

If you skip this move, you end up with a generic Dalio summarizer. Which is what most readers will get the first time they try this without thinking.

Move Two. Get the source material into a Cowork project.

I opened YouTube. Dalio’s Big Cycle video, the 40 minute one from his Principles for Dealing with the Changing World Order book. Free. No login. No Kindle. No DRM headache.

I pulled the transcript using NotebookLM. You can also use the YouTube transcript button directly, or any free transcript tool. Three minutes of work.

This is the part I want every reader to internalize. The author already gave the framework away. Dalio published the entire Big Cycle in a free video. He wrote a long-form essay version on his Economic Principles site. He posts updates on LinkedIn. The book is the deeper version, but for what I was building, the video was actually cleaner. Less philosophy, more operating logic.

For finance, this works almost too well. Marks publishes every memo. Buffett’s letters are free on the Berkshire site. Damodaran teaches his entire valuation course on YouTube. Druckenmiller speeches are on YouTube. Klarman excerpts circulate openly. Most macro thinkers, mostly free, if you know where to look.

Now the execution. I made a folder on my Mac called red-alias-build. Inside it, three subfolders. One called source, one called extraction, one called skill. I saved the transcript as a plain text file inside source. Just a .txt or .md file, anything Cowork can read.

Then I opened Cowork and pointed it at the red-alias-build folder. That folder is now the project. Cowork sees the three subfolders, sees the transcript inside source, and can read it directly. No copy-pasting transcripts into chat windows. No attaching files. The transcript lives on my Mac, Cowork reads from there, and any output Claude produces, I can have it write back into the same folder structure.

This is the entire reason this build runs in Cowork and not anywhere else. The skill is being built out of files that live on your machine, and Cowork is what gives Claude direct access to those files.

Move Three. Extract the operating logic.

This is the move that matters most.

I opened a chat in the Cowork project and ran one prompt. The prompt is the trick. It does not ask Claude to summarize Dalio. It asks Claude to lift the operating logic out and lay it down as raw material I can build with.

Here is the prompt, exactly as I ran it. You can paste it as is. Replace the file path and the job statement with yours.

Read the transcript at source/dalio-big-cycle-transcript.txt.

My job to be done: An equity research analyst, researching a stock with
material exposure to a specific country, who needs Dalio's Big Cycle
framework to run on that country before they commit to the thesis.

Extract three categories of material from the transcript. Be thorough.
Do not summarize. Lift the actual operating logic out, in Dalio's own
terms.

1. EXPLICIT FRAMEWORKS. Named structures, numbered indicators, staged
sequences. Anything Dalio explicitly lays out as a framework.

2. IMPLICIT MENTAL MODELS. How Dalio reasons about cause and effect.
The recurring patterns and tradeoffs that are not packaged as numbered
steps but show up across the transcript.

3. IF-THEN RULES. Decision rules embedded in the transcript. Format
each as: IF [condition], THEN [implication]. These will become the
operating logic of the skill.

For each item, note which part of the transcript it comes from. Flag
which items map most directly to my job statement. Do not invent rules
that are not in the source.

Save the output as extraction/dalio-big-cycle-extraction.md in this
project.

What came back was a structured extraction. Dalio’s eight power indicators, laid out clean. The three phases of the Big Cycle. The three trigger conditions for a regime change. A list of if-then rules pulled from his own examples. The wealth gap mechanics. The reserve currency trap. The internal-versus-external war pattern.

Because I asked Claude to save it to the extraction subfolder, the file landed there as a real markdown file. I opened it in TextEdit, read it once, made sure it was clean. The 40-minute video had been compressed, without loss, into 1,200 words of operating logic sitting on my Mac.

Move Four. Write the SKILL.md and install it.

Now I had everything. A job statement. A clean extraction file. I asked Claude to write the SKILL.md, with one specific instruction. Use only the extracted material. Do not add frameworks the source does not support. Stay tight to the job statement.

The prompt was short.

Read extraction/dalio-big-cycle-extraction.md. Using only that
extraction, write a SKILL.md file for a Claude skill named red-alias.

The skill must:
- Take a country (and optionally a sector or stock) as input.
- Produce a fixed set of outputs that map to my job statement.
- Use only Dalio's framework as extracted. Do not invent.
- Stay strictly country-level. No DCF, no price target, no model, no
  buy-sell view.
- Embed the if-then rules from the extraction as decision logic.
- End every run with a closing line that hands the thesis and model
  back to the analyst.

Format as a standard SKILL.md with YAML frontmatter, a role definition,
clearly numbered outputs, decision logic, output format, what the skill
does not do, and rules.

Save the output as skill/red-alias.md in this project.

The file came back clean on the first pass. I tightened a few lines, killed a section that was redundant, and locked the final version. The whole build, from the moment I clicked play on the YouTube video to the moment I had a working SKILL.md sitting in the skill subfolder, took about ninety minutes.

Now, on Claude Cowork, upload the file in a skills subsection inside your customize section, Claude loads it automatically.

If you want the SKILL.md as a clean download, plus a one-page install guide with screenshots, the companion PDF is on shikshannivesh.com.

The skill, ready to install.

Below is red-alias.md. Copy it, save it as red-alias.md, drop it in your skills folder, and the skill is live. If you are running this in Claude Projects on the free tier instead of Cowork, paste the contents into your project instructions. It works either way.

Once installed, you call it the way you call any skill. Open a chat in the project, name a country, name the sector or stock you are researching, give your one-line thesis if you have one, and ask Claude to run a Big Cycle check.

I have run it on India, the US, China, and Vietnam in the last week. The output that has stayed with me is the pressure questions. The skill returns three to five questions tied to the regime read, and they are the questions a senior PM would actually ask if they sat across the table from your thesis. They are uncomfortable in a useful way.

That is the whole build. Four moves. The artifact below is the proof.

---
name: red-alias
description: >
  Country-level macro risk lens for equity research. Use when researching a
  stock, sector, or thesis with material exposure to a specific country,
  before committing to the position. Runs Dalio's Big Cycle framework on
  the country, scores it across eight power indicators, and pressure-tests
  the analyst's thesis against the country's regime read. Trigger phrases:
  "run a country lens on", "Big Cycle check", "macro regime read on
  [country]", "pressure-test my thesis on".
---

# Red Alias

You are a senior macro strategist sitting across from an equity research
analyst. The analyst has a thesis on a stock or sector with exposure to a
specific country. Your job is to run a Big Cycle country regime check
before they commit to the position. You are direct, structured, and you
do not flatter the analyst's thesis. You ask the questions a senior PM
would ask.

## Your Role

You apply Ray Dalio's Big Cycle framework to a single country at a time.
You do not output price targets. You do not output models. You do not
recommend buying or selling anything. You produce a regime read and a
set of pressure questions. The analyst owns the thesis and the model.
You make sure the country regime is checked before the model gets built.

## Inputs You Need

Before running the lens, ask the analyst for these in one message. Do not
ask one at a time.

1. The country in focus.
2. The sector or stock they are researching, if any.
3. Their one-line thesis, if they have one. If they do not, that is fine.
   Note it and proceed.
4. Whether they want a quick read (the five outputs in compact form) or a
   full read (each output expanded with reasoning).

If the analyst gives you only a stock ticker without naming the country,
infer the country of primary exposure from the ticker and confirm it with
them in one line before proceeding.

## The Five Outputs

Produce these in order, every time. Always all five. Do not skip any.

### Output 1: Big Cycle Stage Read

State which phase of the Big Cycle the country is in. Choose one.

- Rise (early, mid, or late)
- Top
- Decline (early, mid, or late)
- Post-decline / regime reset

Justify in two to three sentences. Reference the country's recent debt
trajectory, trade share trajectory, and currency status. If the country
sits ambiguously between two phases, say so and explain the tension.

### Output 2: Eight Indicator Scorecard

Score the country on Dalio's eight power indicators. Use a simple table.
Each indicator gets one of three states: Rising, Stable, Declining.
Justify each score in one line.

| Indicator | State | One-line rationale |
|---|---|---|
| Education | | |
| Innovation and technology | | |
| Competitiveness in global markets | | |
| Economic output | | |
| Share of world trade | | |
| Military strength | | |
| Financial center strength | | |
| Currency / reserve currency status | | |

After the table, name the two indicators that are moving fastest in
either direction. These are the highest-signal indicators for the
analyst's time horizon.

### Output 3: Internal Order Read

Classify the country's internal order as Stable, Stressed, or Breakdown.

Look for:
- Wealth gap trajectory
- Political polarization (left and right populism)
- Capital flight signals (the rich moving wealth out)
- Tax and regulatory risk on capital and the wealthy
- Social cohesion signals

State the classification in one line. Then list the two or three
strongest signals supporting it.

### Output 4: External Order Read

Classify the country's external order as Stable, Stressed, or Breakdown.

Look for:
- Trade share trajectory versus rivals
- Military spending and reach versus rivals
- Reserve currency or currency international usage trajectory
- Geopolitical alignment shifts
- Recent escalation with rivals

State the classification in one line. Then list the two or three
strongest signals supporting it.

### Output 5: Thesis Pressure Questions

Generate three to five pressure questions. Each question must be tied
to a specific finding in Outputs 1 through 4.

Format each question as:
- The question itself, in the analyst's language.
- The regime finding it is anchored in (one short phrase).
- What breaks in the thesis if the analyst cannot answer it.

Pressure questions should always include at least one of each:
- A debt cycle question.
- A currency or capital flow question.
- An internal order question (regulatory, tax, or political risk).

If the analyst gave you a thesis, anchor the questions to that thesis.
If they did not, anchor the questions to the sector or stock they named.
If they gave neither, anchor the questions to the country's most exposed
sectors based on the regime read.

## Decision Logic

Apply these rules from Dalio's framework when forming the outputs.

IF the country has hit zero rates and is still printing money, THEN the
country is in late-stage debt cycle. Flag this in Output 1.

IF the country's central bank is actively printing money to relieve a
crisis, THEN flag rising risk to currency value and rising support for
hard assets. Reflect this in Output 4.

IF wealth gaps are widening alongside left-right populism, THEN the
internal order classification cannot be Stable. Default to Stressed at
minimum.

IF the rich in the country are visibly moving wealth out (offshore
accounts, foreign property, foreign currency holdings, second
citizenships), THEN classify the internal order as at least Stressed,
and flag capital control risk.

IF the country is losing trade share to a specific rival year over year
for three or more years, THEN flag the country as at or past Top in
Output 1.

IF a rising rival has built a military comparable to the country, THEN
external order is at least Stressed, and Output 5 must include a
geopolitical pressure question.

IF the country's debt is mostly domestic and in its own currency, THEN
note that the country has more flexibility to inflate the debt away
without an immediate currency crisis. Adjust the urgency of debt-related
pressure questions accordingly.

IF the country's debt is mostly held by foreign lenders, THEN flag
elevated currency crisis risk in Output 4 and include a currency
pressure question in Output 5.

IF all three of Dalio's trigger conditions are met (unpayable debt at
zero rates, internal conflict over wealth and values, rising external
rival), THEN explicitly state in Output 1 that the country is in a
regime change window. This is the highest-severity classification the
skill produces.

## Output Format

Produce the five outputs in order, with the headers above. Use tables
where specified. Use prose for the rest. Do not use bullet points
inside Outputs 1, 3, and 4 unless listing signals. Keep each output
tight. Compact mode targets 400 words total. Full mode targets 1,200
words total.

End every run with a single line:

> Country regime read complete. The thesis and the model are yours to
> build. This skill checked the regime before you committed.

## What This Skill Does Not Do

- Does not output a price target.
- Does not output a DCF or any valuation.
- Does not recommend buying, selling, or holding.
- Does not model the stock or build the financial statements.
- Does not run a Kill Report-style forensic check on the company. That
  is a separate skill.
- Does not score sub-national regions, individual states, or cities.
  Country level only.

## Rules

- One country at a time. If the analyst names two countries, run the
  skill twice.
- Always produce all five outputs. Never skip Output 5.
- Use Dalio's terminology where it adds clarity (Big Cycle, internal
  order, external order, reserve currency status). Do not use it as
  decoration.
- If the data is genuinely uncertain, say so. Do not invent indicator
  scores. Mark uncertain indicators as "Uncertain" in the scorecard
  and explain in the rationale column.
- Stay in the lane of macro country risk. The analyst's stock work is
  not your job.

If you want the SKILL.md as a clean download, plus a one-page install guide, the companion PDF is on shikshannivesh.com , Same content, easier to keep on your desk.

As We End This Edition

I have watched the Dalio Big Cycle video eleven times. I have read it zero times.

That used to feel like a failure. It does not anymore.

The book is still on the shelf. Principles, Big Debt Crises, Changing World Order, The Intelligent Investor, Built to Last. They are still there. I will probably still not finish most of them this year.

What is different now is that one of those frameworks has left the shelf and entered my workflow. Every stock I research with cross-border exposure, the country goes through red-alias before I commit to the thesis. Dalio’s Big Cycle, applied automatically, every time, in the same shape. Not because I am more disciplined. Because the skill carries the discipline for me.

The shelf has four more books on it. Four more frameworks waiting to be lifted out. Four more skills that can live in my Equity Research project by the end of the next quarter. Marks on cycles. Klarman on margin of safety. Collins on what separates good companies from great ones. Damodaran on narrative and numbers.

The reading problem was never a reading problem. It was a workflow problem. Books deliver frameworks as prose. Research workflows need them as prompts. Once you see the gap, you cannot unsee it.

The four moves work for any book on your shelf. Find the source, often a free video or essay the author has already published. Extract the operating logic. Write the SKILL.md. Install it.

If you want the next skill to be Marks, run the same four moves on his memos. If you want it to be Klarman, run them on the Margin of Safety excerpts that circulate openly. If you want it to be Damodaran, run them on his free YouTube valuation course. The pattern is the same. Only the source changes.

The last time I wrote about a macro setup that mattered to my readers, I shared the full workflow in The Mistake That Cost 12 Months and the System That Fixed It. That workflow runs the macro analysis manually, end to end, for any country, any trigger. red-alias is the upstream check. It runs before that workflow, on the country regime itself, so the manual analysis starts from a regime read instead of a blank page.

The two work together. The country lens first. Then the macro workflow. Then the stock model. Each one earns its place in the stack.

The shelf has more books on it. The stack has more lenses to add.

The launch offer

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 →

🧰 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 all live in one place: 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.

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.

Claim 25% off →

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, from one window.

Attempt twenty-one stuck.

This is what I wish someone had told me before attempt one.

Before we go further — a confession, and a reframe

If you’ve been following Alpha with AI for a while, you know I’ve spent months teaching Claude Cowork. The interface. The projects. The skills library. The $100K Research Framework I published earlier this month runs entirely on Cowork.

I’m not walking any of that back. Cowork is the right tool for most of what most analysts do, most of the time.

But I owe you the truth about something.

There is a layer underneath Cowork. It’s called Claude Code. And once you cross over, you don’t go back for the heavy lifting.

Think of it like this.

Cowork is your Bloomberg terminal interface: visual, guided, polished, curated. Everything you need is a click away. No learning curve beyond knowing where to click.

Claude Code is the raw data feed: direct, unfiltered, infinitely configurable. Every senior trader who’s spent ten years on a desk eventually memorises the keyboard shortcuts and stops using the mouse. It’s not that the mouse is bad. It’s that the shortcuts are faster, deeper, and do things the mouse can’t.

Same thing here. Cowork got me in the door. Claude Code is what I reach for when I want to do things Cowork can’t do.

Today’s story is about one of those things.

What I was chasing, and why I kept quitting

Here’s the problem I’ve been trying to solve for about a year.

My research library is enormous. Annual reports going back five years for every company I cover. Earnings call transcripts. Sector reports from McKinsey, BCG, Deloitte, and every Indian consultancy worth reading. Regulatory filings. Trade body publications. My own notes and memos. Thousands of pages across hundreds of PDFs.

All of it useless when I actually need to answer a question.

Because when I want to check something, “has management mentioned China+1 in the last four concalls?” — I can’t just ask. I have to open each PDF, use Ctrl-F, scroll through, read context, copy-paste into a doc. Repeat for each source. Forty minutes later I have an answer.

“But wait, I already have Drive connected to Claude and Notion connected to ChatGPT.” I hear you. So do I, and I use both. But those connectors blend your files with the model’s training data, and they pick the top few matching chunks rather than read everything. That’s fine for finding a slide; it’s the reason I lost months of research in early 2024 when I trusted AI outputs I couldn’t verify. NotebookLM solved that for me, if the answer isn’t in your sources, it says so, and every claim comes with a citation you can click through to the exact passage. That story sits at the heart of the industry research playbook.

But here’s where I stayed stuck for a year.

NotebookLM is a website. Every query lives in my browser. I can’t reach it from other tools. I can’t chain it into a workflow. I can’t hand it to my research process, it’s a separate app I have to remember to open. Even once I was using NotebookLM religiously, I was the bridge between it and everything else. Manually.

What I wanted was for my NotebookLM notebook to be a service. Something Claude could call on its own. Something that sat behind everything else I was building.

That’s exactly what Claude Code + NotebookLM does.

The moment it clicked

Last week I found a skill on GitHub called notebooklm-py. Unofficial, built by a developer named Teng Lin. 10,400 stars. The description was simple: it lets AI agents like Claude Code talk directly to your NotebookLM notebooks.

I installed it on my Mac.

Fifteen minutes later, I was asking Claude Code a question about the specialty chemicals industry, and Claude was reaching into my NotebookLM notebook, querying only the sources I’d approved, and answering me with citations pulled from my own library.

No copy-paste. No browser tab. No Ctrl-F.

Just a conversation with a research assistant who had already read everything in my folder.

That’s the moment I should have had two years ago.

Okay, but isn’t Claude Code for coders?

This is where I stopped the first twenty times, so let’s handle it head-on.

Claude Code looks like it’s for coders. The screenshots you’ve seen online usually show a terminal window with green text and a lot of what looks like magic. That’s intimidating. It intimidated me for two years.

Here’s what I learned on attempt twenty-one:

Claude Code is not a coding tool. It is Claude, with hands.

It’s the same Claude you talk to in the chat window. Same voice, same intelligence. The only difference is that this version of Claude can read files on your computer, run commands on your behalf, and install skills that extend what it can do. The “coding” part is just one of the many things it can do and unless you ask it to write code, it won’t.

Better still, you don’t have to live in a terminal.

Claude Code runs in three places:

1. Inside Cursor: an app that looks and feels like a chat window, with the power of Claude Code underneath. This is what I use, and it’s what I’ll walk you through below. Cursor is “VS Code on steroids” if that means anything to you. If it doesn’t, forget the phrase, Cursor is just a clean, quiet app where you type questions to Claude and watch it work.

2. Inside the Claude desktop app: the same Claude app you already use. Claude Code lives inside it now as a feature. No separate tool to install. If you want the softest possible entry, start here.

3. In your terminal: the hardcore option. You don’t need this. I barely use it.

Two paths, one destination. Pick whichever one looks less scary.

The install — plain English, nothing hidden

Before we start, one thing you need to internalise. It’ll change the whole experience.

If anything in this section throws an error, don’t think. Don’t Google. Don’t panic. Copy the error message, paste it into Claude (the regular chat window you already know), and tell it: “I’m installing Claude Code and ran into this. Help me fix it.” Nine times out of ten, Claude will give you the exact next command to run. If you want to go nuclear, paste this entire section of the newsletter into Claude along with the error, it’ll know exactly where you are in the process and what to try.

You’re not debugging as a programmer. You’re handing an error back to Claude and asking for the fix. That’s it. Keep that in your back pocket, and the fear of the terminal disappears.

Two reference pages worth bookmarking, if you want to go deeper, or if Claude needs context to help you debug, feed it these:

• Official Claude Code setup docs: code.claude.com/docs/en/setup

• The NotebookLM skill GitHub page: github.com/teng-lin/notebooklm-py

Now, pick your path before we start.

Step 1: Pick your path

There are two ways to get Claude Code running on your machine. Pick the one that fits you. You don’t do both.

Path A: Claude desktop app (easiest, no terminal). If you already have the Claude desktop app installed, you’re most of the way there. Claude Code is built into the desktop app as a separate section in the sidebar. No terminal, no install commands, no config files. If you don’t have the app yet, download it from claude.ai/download, install it, open it, find the Claude Code section, sign in with your Claude Pro ($20/month) or Max subscription. Done.

If you pick Path A, skip straight to Step 4. You can ignore Steps 2 and 3.

Path B: Terminal + Cursor (what I use). More power, slightly more setup. Claude Code runs as its own tool on your computer, and you talk to it inside Cursor, a clean workspace that feels like a chat window with Claude’s full agentic capability behind it. This is the path I personally use for serious research work.

If you pick Path B, continue to Step 2.

Step 2: (Path B only) Install Claude Code

No Node.js. No app downloads. One command in your terminal. Anthropic now ships a native installer that handles everything in one step.

On Mac, open Terminal (hit Cmd + Space, type terminal, press Enter), paste this, press Enter:

curl -fsSL https://claude.ai/install.sh | bash

On Windows, open PowerShell (hit the Windows key, type powershell, press Enter), paste this, press Enter:

irm https://claude.ai/install.ps1 | iex

Plain English for both: “Go to Anthropic’s website, download the Claude Code installer, and run it.”

Windows users: if the installer tells you it needs Git for Windows, let it guide you through that or download it yourself from git-scm.com before running the command above. Git for Windows is a one-time install; Claude Code uses it under the hood. Leave all the default settings when you install it.

When the installer finishes, close your terminal window and open a new one. This matters, your computer needs a fresh terminal session to recognise that Claude Code is now installed.

Then sign in. Type this into your fresh terminal and press Enter:

claude

Plain English: “Start Claude Code.”

Now it may ask you to log in via Anthropic API or OAuth your Claude subscription. You can choose your Claude subscription.

A browser tab opens and asks you to sign in. Use your Claude Pro ($20/month) or Max subscription. Either works. Done.

Step 3: (Path B only) Install Cursor

Download Cursor from cursor.com. Install it like any other app. Open it. It looks like a clean code editor, don’t let that scare you; you won’t be coding. It has a chat sidebar where you talk to Claude Code. That’s the window you’ll live in from here on.

Step 4: Install the NotebookLM skill (everyone does this step)

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, 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.

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’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

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 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.

Read more