A Chinese company known for selling smartphones entered one of the hardest industries in the world…

…and its first EV sold more units in China than Tesla’s Model 3!

And they are not the exception.

Last year, China produced 75% of the world’s electric cars.

And it’s not just EVs…

China now controls 85% of the global solar supply chain.

Today, they can manufacture 2x the solar panels the world uses each year.

Yes, you read that right: 2X the world needs!

We know that when China enters massivly an industry:

1. The local capacity grows fast.

2. Prices fall as competition intensifies.

3. Margins get squeezed across the global industry.

4. Stock prices fall for decisions China made years ago.

1408 days separated China’s EV plan from the first German automaker profit warning linked to Chinese competition.

As investors, the earlier we see this coming, the better.

I built a Claude workflow tha scans “the China risk” for any industry or stock and find:

• which sectors China is pushing into

• If a company you own could get hit and how

• what to watch before the market notices

Follow the steps below and use the prompts and Skills I’m sharing to run your own China risk analysis on any stock or industry.

Let’s dive in:

The China risk scan with claude:

The pattern is always the same:

1. China picks an industry :It puts it in its 国民经济和社会发展五年规划纲要

For non-Mandarin speakers like me, that means theire 5 Year Plan.

2. Money follows:
Capital, subsidies, infrastructure, and new companies move into that industry.

3. The local market helps companies scale:
China’s huge home market lets them grow fast , build more capacity, and cut costs.

4. The strongest players go global:
Once they reach scale, they start exporting everywhere.

Any business with no real moat, can quickly start a race to the bottom.

Let’s use this 3-step Claude workflow to find where China could disrupt next:

• Step 1: Analyze China’s 5 Year Plan

• Step 2: Map the impact on any industry

• Step 3: Map the impact on any stock

Step 1: Analyze China’s 5 Year Plan :

We first need to understand what China is actually planning.

The latest 5 Year Plan was released in March 2026.

The problem?

It is a long, complex document written in Chinese.

Perfect job for AI.

With one prompt, you can turn it into a report showing:

China’s priority industries :

What China is trying to achieve in each sector :

Use this prompt in Claude (or any other LLM to have an interactive web page that explains the plan in plain English:

Read more

So No,

I’m not going to show you how to use AI to guess when the Fed will raise interest rates…

We already know that the Fed did’t raise rates on last meeting, but 3 members voted for a raise.

As an investor, I wan to answer this simple question:

How would a rate hike or any economic event impact a company I own?

And I don’t want a lazy answer like:

“Rates go up, so tech stocks go down.”

I want to understand the impact on the business itself.

• Could higher rates slow customer spending?

• Pressure margins?

• Increase funding costs?

• Help competitors with stronger balance sheets?

• Or create an opportunity for the company to gain market share?

I did teach Claude how to take any economic event for any stock, then deliver a full report showing:

• How the macro event reaches the business

• What changes in revenue, margins, cash flow, and the balance sheet

• And what to monitor next

Subscribe now

How to turn any macro event into a clear business impact analysis:

Claude is especially useful for this kind of analysis because:

• He can test several scenarios and go deeper than we can manually.

• He can compare the current situation with similar periods in the past and see what happened.

• And will summarize the output in a structured way, helping spot what we may miss manually.

But please don’t get too excited…

Claude will not do all of that from a simple question like:

“What is the impact of higher rates on Meta?”

I tried it:

I got a few generic points but not enough to challenge an investment thesis.

Now let’s compare that with the Skill I built for this exact task.

I asked the same question:

But this time, Claude followed a clear investing framework.

The result was 10X better.
First, I got an executive summary that gave me the key findings in a few minutes.

And the report ends with a full business impact analysis, broken down the way I like to think about any business :

The difference came from giving Claude a proper process to follow with the skill

Build the system in 2 steps:

We will use Claude Cowork.

We can also do this in regular Claude, but Cowork gives better results because Claude can read the full business history before starting the analysis.

Download the Skill called “macro-to-micro-thesis-tracker “from the Skill Library and run it whenever you want to test how a macro event could affect a stock.

Read more

The other half is what it takes to earn it.

Imagine 2 businesses:

• both grow sales by 20%.

• both added $3 of revenue last year.

• one spent $1 of capital to get there.

• the other needed to spend $3 for the same growth.

These are completely different businesses.

The difference only shows up in the balance sheet.

You may think:

Okay Mostapha, I know that I need to read the balance sheet carefully...

But there is a trap.

Reading latest balance sheet does not give you the full picture.

You need the last 5–7 years to understand how the business is evolving.

7 years ago , a company needed $1 of capital to grow 20% .

Today, it needs $3 to have the same growth.

Should investors still pay the same multiple for that business?

Probably not.

But we all know that reading 7 years of balance sheets takes hours and hours of work.

This is where AI can save you real time.

I built a Claude Skill that answers the main balance sheet questions in 30 minutes instead of 5 hours :

• Where could the balance sheet break?

• How much capital does growth require?

• Is the business becoming more or less capital intensive?

• Who is funding the assets: shareholders, lenders, customers, or suppliers?

Here is what the Skill found when I ran it on Microsoft:

Subscribe now

Claude shows how Microsoft used to run on other people’s money:

• Customers paid for Office up front.

• Supplier bills had not yet been paid.

• Salaries had not yet reached employees’ bank accounts.

In 2019, this pile of free funding covered 97% of the assets Microsoft needed to operate.

Then Microsoft started building data centres..

And data centres require a lot more capital.

Claude shows how every $100 of Microsoft’s assets was financed in 2019 compared with 2025:

By the end of this article, you download a Claude Skill and use it to analyze years of balance sheets for any stock.

Want the ready to use Skill?

Paid members can download this Balance Sheet Skill and run it on any stock immediately.

You also get full access to the Investing AI Library, including every prompt and Skill I build for research, earnings analysis, thesis testing, and more.

3 Steps to build the balance sheet analyst

Read more

I use the same AI process for every company.

It helps me research faster and make better investment decisions.

But how do you build that?

1. Learn the basics of AI: Know what it does well, where it fails, and how to give clear instructions.

2. Write down how you invest without AI: List each step, from learning about the business to making your final choice.

3. Test AI at each step: Try different tools, prompts, and Skills. Keep the ones that save time or help you think better.

4. When something works, turn it into a clear process: Write down what files to add, what prompt to use, and what the final result should include.

5. Repeat this for every part of your research: In the end, you will have one AI process you can use for any stock.

“But Mostapha, this takes time...”

Yes!

Who said building the equivalent of a team of 5 analysts working for you would be easy?

The good news is that you do not have to start from 0.

For the past year, I have built and tested a full AI investing system.

You can copy the full system, start using it today, and then adapt it to your own investing style.

Here is how it works:

The 5-Step AI Investing Research Loop:

Subscribe now

Filter → Understand → Deep Dive → Build and Break → Update

AI does not play the same role at every stage.

The purpose of the framework is simple:

Use AI for the right task, at the right moment, without losing control of the investment decision.

For each step, I will explain its purpose and give you the exact AI prompt or Skill to use.

Let’s see exactly how to use AI at each stage:

Read more

What annual return can I reasonably expect from this stock?

And there are 2 terrible ways to answer it:

1. The spreadsheet answer:

• A big DCF model.

• An 8.73% discount rate.

• A 2.14% long-term growth rate

Final answer:

Fair value: $147.32.
I should make exactly 17.52% a year.

Not 17%…Exactly 17.52%.

Because apparently they can predict the future down to 32 cents…

2. The vibes answer:

Great company. Huge market.

This can compound at 20% a year.

Maybe.But where does the 20% come from?

Both answers miss the point.

• The DCF gives false precision.

• The vibes answer gives no real explanation.

I use something simpler, but based on how the business works:

I expect about 20% a year:

15% from earnings growth, including 13% from volume and 2% from pricing.

+5% a year from a higher valuation multiple.

Now I know exactly what I am betting on.

• Pricing: Can the company raise prices without hurting demand?

• Volume: Can it really grow 13% a year? From new countries, more customers, or more usage from existing customers?

• Margins: How much margin expansion is still left, and how much can it add to earnings growth?

• Valuation: Does the stock still work if the multiple stays flat?

I taught Claude this way of thinking.

Then I turned it into a ready-to-use Skill called The Expected Return Check.

You can use it whenever you want to test the expected return of any stock.

Subscribe now

Start with the return, then work backwards:

Let’s say you are studying Netflix

You want to know whether the stock can return 20% a year over the next 5 years.

• You go to Claude

• You call the skill “Expected Return Check”

• You give it a stock, a target annual return, and a time horizon. ( Netflix exemple: )

In minutes, Claude creates an interactive web page with:

• The investment case: what the business must do to reach your target return.

• The key drivers: where Volume, Price, Mix, and Margin stand today, and what each one must add.

• a simulator: change the business drivers or exit multiple.

  Test Bear, Base, and Bull cases and see the expected return update at once.

Take a look at the Netflix results here: link

How to Use It :

This Skill works in the normal Claude web app.

You do not need Claude Cowork app.

Upload the Expected Return Check from the Skills Library, where I’ve grouped 20+ ready-to-use investing Skills in one place.

From this link :

Read more

• “Europe is hot and nobody has AC.”

• “Markets are crazy and people are trading more.”

• “3 AI IPOs could suck up $200B. That money has to come from somewhere.”

All of these are common-sense observations.

As investors, our job is to answer 2 questions:

1. What industries and businesses benefit from this trend?

2. And what bets are already crowded?

But if you have never studied that industry before, the answer can be painfully long..

And you can guess the solution:

We have AI

I built a Claude workflow that takes a simple observation and turns it into:

1. The likely winners and losers

2. An explanation of the value chain of the related industries

3. A guide that shows you how the industry works in hours, not days.

By the end of this article, you’ll have the system ready to use every time you see something in the market and wonder: “Who benefits from this?”

Subscribe now

How the workflow works:

You only need to use my 2 Claude Skills.

1. The first finds the industries behind the trend.

2. The secondt eaches you how one of those industries works.

Step 1: Find the Industries Behind the Trend

Let’s use this observation:

Europe is getting hotter, and nobody has AC.

So inside Claude, I run:

A few minutes later, Claude gives me an interactive page.

It breaks the observation into 3 layers:

• First-order effects :The obvious beneficiaries.

• Second-order effects :The infrastructure that needs to adapt.

• Third-order effects :The slower changes people usually miss.

And it also shows the wrong side of the trend like

River-cooled power generation or Alpine ski tourism.

Also in same page , Claude ranks the industries by:

• direct vs indirect exposure,

• durable vs passing trend,

• crowded vs overlooked,

Share

Step 2: Learn the basics of the industry

Now we have the shortlist.

Before looking for stocks, you need to understand how the industry works.

• Who makes money?

• What metrics matter?

• Who has pricing power?

So I use the second Claude Skill like this :

A few minutes later, Claude builds an interactive learning page like this one:

A practical guide made for investors that gives:

1. The jargon explained in plain English

2. A clear 1-page summary of how the industry works

3. Clear next steps on what to read, what to analyze, and how to go deeper

   ---

How to use it

Step 1: Install the Skill once.

• Download the 2 Skills (link below)

Read more

I was recently invited on a podcast to talk about how I use AI in investing.

You can listen here:

Spotify Link :

Or on substack :

Compound with René

AI as Your Research Team? Inside a Modern Investing Workflow (with Compound with AI)

In this episode, I sit down with the mind behind Compound With AI, the French investor who has built the most-followed account at the intersection of artificial intelligence and investing – now past 61,000 subscribers, ahead of even Aswath Damodaran, the…

Listen now

a month ago · 4 likes · René Sellmann

Hope you enjoy it,

Mostapha

Subscribe now

That message showed up last week in our investor group.

The stock was up almost 10x in a year on AI hype.

Everyone was talking about it on X.

Then the short-seller report came out.

A few days later, the stock was down 50%.

That’s when I asked myself:

Why wait for the short seller?

Why not make Claude run the short-seller check for any stock.

So I built a Claude agent for that.

In one click, claude will:

1. Check filings and numbers: cash flow, receivables, debt, margins, and related-party red flags.

2. Compare the management story with what the numbers actually show.

3. write a short-seller report: what looks strange, what needs proof, and what could break the thesis.

The output is an interactive page you can export into a doc like this one:

You can download the agent, copy it, and run it every time you doubt

Subscribe now

How the Claude Short-Seller Check Works

99% of stocks are not frauds…

But you only need to be trapped once to lose a lot of capital.

That’s why I built this Claude Agent like a small investigation team.

You give it one company.

Claude sends 3 detectives into the stock.

Detective 1: People Check

this one answers a simple question

Can you trust the people running the company?

It looks for past scandals, lawsuits, insider selling, strange related-party deals, and signs of self-dealing.

Because fraud usually starts with people.

Detective 2: Numbers Check

The key question:

Are profits showing up in cash?

Or only on paper?

Detective 3: Real World Check

Does the business exist at the size management claims?

Because a company can tell a beautiful story.

But factories, stores, customers, and cash are harder to fake.

At the end, Claude gives you a short-seller report:

• What looks strange

• What needs proof

• What would make the fraud case stronger

• What would prove the short thesis wrong

How to Install the Claude Short-Seller Agent

To use this agent, you need Claude.

The idea is simple:

• Download my file.

• Upload it into Claude.

• Then use it every time you want to check a stock for red flags.

Here are the exact steps:

Read more

But now you need to understand the people behind the business.

So you open Claude.

And in a click, you get a clean management report that answers:

• How much stock do they own?

• Are they paid like owners or employees?

• Do they use every dollar where it creates the most value?

• How they used shareholders’ cash: reinvestment, buybacks, debt, or deals.

• What they did when the stock crashed and the business was under pressure.

  

I called it management-incentive-check.

1 Claude Skill.

to answer 1 question:

Can I trust this team with my capital for the next 5–10 years?

You can download it once and use it on any stock.

But first, let me show you what happens behind the scenes.

Let Claude Do the Hard Work

Behind this 1 click report is a lot of ugly work.

• Filings.

• Proxies.

• Compensation tables.

• Capital allocation history.

The kind of work most investors know they should do…

but rarely do properly.

That is where claude does the digging.

You keep the judgment.

Subscribe now

The principle is simple:

Follow the money and past actions

Anyone can say:

“We think like owners.”

What is harder to fake over 10 years?

Where the cash actually goes.

I ran it on Spotify.

Here’s an exemple on what came out:

On capital allocation:

On the outsider tests:

How to run it:

You can use Claude anywhere.

But the best place is Cowork.

Why?

Because Cowork can open your existing projects:

filings, notes, past research, thesis files.

So Claude does not start from zero.

New to Cowork?

I wrote a full guide here.

I highly recommend reading it first if you haven’t yet.

Step 1: Install the Skill once.

• Download the Skill file (link below)

Read more

The thesis makes sense.
The business looks good.
The valuation looks reasonable.

But one question is still open:

What happens to your portfolio if you add this stock?

Does it add something new?
Or just more of what you already have?

• You open Claude.

• And in one click…

• Claude gives you a portfolio X-Ray like this:

A clean report showing what your portfolio is really betting on.

1. Your real portfolio exposures

2. The stocks that depend on the same drivers

3. The positions creating hidden concentration

4. The holdings that actually diversify the portfolio

This is possible with the Portfolio X-Ray I’m sharing with you.

• Download it.

• Upload it to Claude.

• And run it on your portfolio.

Subscribe now

How to make claude your portfolio auditor:

The idea is to use Claude for 2 jobs :

1. Review your portfolio to see what you really own:

Claude looks beyond sectors and tickers.

It maps the forces that actually drive your holdings:

• AI capex

• Oil prices

• Interest rates

• Credit conditions

• Consumer spending

This shows the forces your portfolio keeps betting on, not just the stocks you own.

I would run this once a quarter to challenge my own portfolio.

2. Test a portfolio move to see what it really changes:

This is for any add, sell, or resize decision.

Claude shows the impact of the move:

• What exposure grew?

• What exposure shrank?

• What new overlap appeared?

• What diversifier disappeared?

In the video, I show you how to run it on a real portfolio:

What Happens Behind the X-Ray

We’ll use a Claude Skill for this.

If you have never used a Skill, don’t worry.

You don’t need a complex setup.
You only need Claude in the browser.

Once the Skill is uploaded, you can run it in 1 click.

How to use it

Step 1: Install the Skill once.

• Download the Skill file (link below)

Read more

• You find a new stock, learn the business 10X faster.

• You want to go deeper, find answers across years of filings.

• The stock deserves a closer look, build a thesis and challenge it.

• The company reports earnings, see what changed and what to watch.

A living research system inside Claude that evolves with the company over time.

By the end of this article, you’ll have a ready-to-use system to research any stock 10X faster.

You’ll get everything you need:

the skills, the prompts, and the step-by-step setup guide.

How Claude Becomes a Stock Analyst:

(Cowork + Project Instructions + Skills)

The idea is simple but powerful:

1 stock = 1 Claude project.

Everything about that company lives in one place.

Then we will use Claude’s most powerful features.

1. Cowork : So Claude can read the files on your computer.

2. Skills : So Claude can run the same research workflows again and again.

3. Project Instructions: So Claude knows what to trust, what to focus on, and how to analyze the company.

The result is a stock research system that gets more useful every time you use it.

Subscribe now

Think of it like training a junior analyst.

• Project instructions teach the analyst your investment process.

• Cowork allows the analyst access to every filing, and research document.

• Skills and prompts give the analyst specialized tools for business analysis.

and unlike a real analyst, this one works 24/7 and never asks for a raise..

in this video, I show some real use cases we can build with this system.

How to Build Your Own Stock Analyst (Step by Step)

We’ll use Claude Cowork.

Don’t worry if you’ve never used it before. It’s easy to set up.

(If you already use Cowork, feel free to jump straight to Step 1.)

Normally, Claude can only see what you paste into the chat.

With Cowork, Claude can access the folders, filings, transcripts, presentations, and research stored on your desktop.

This solves one of the biggest limitations of AI for investors:

• Instead of uploading the same documents over and over again, Claude can find and use them when needed.

• and more importantly, you stay in control of the sources.

You decide which filings, transcripts, presentations, and research documents are available to Claude.

To get started:

• Go to Claude website.

• Download the desktop app.

• Open the desktop app.

• Click Cowork.

  

  ---

Step 1: Create a Permanent Home for the Company

We’ll use Claude Projects inside Claude Cowork.

Why?

Because a project gives Claude a dedicated workspace for a single company.

• It can stay connected to the files on your computer.

• It can keep company-specific instructions.

• And it can store the research you build over time.

1.Creat a stock folder on your desktop

On your computer, create a folder for the company like i have done :

Don’t worry about what’s inside yet.

We’ll build the structure later ( automatically)

2. Create a New Claude Project

Open Claude Cowork and click New Project.

3. Select “Use an Existing Folder”

Choose the company folder you created in Step 1.

This connects Claude to the files that will live inside that folder.

Give the Project a Clear Name ( stock name)

4.Add Project Instructions

This is the first real hack.

Project Instructions are permanent instructions attached to the project.

This means you don’t need to repeat the same rules every time.

These instructions tell Claude:

• What sources to trust.

• What topics to focus on.

• How to use prior research.

• How to tie findings back to the investment case.

The result is better answers, more consistent research, and fewer hallucinations.

Paste the instruction prompt below into your project:

Read more

You open Claude.

One click.

Minutes later, you see:

• Who owns it

• Why they bought it

• What they believe will drive the stock retunrs

• ans questions you should answer before investing

Instead of starting from zero...

you start with years of investor research

Here’s a short video showing what the final result looks like (sound on).

Subscribe now

Borrow the Research, Not the Conviction

This system turns elite investor research into a faster starting point.

Not to pick stocks for you.

To show who owns it and why.
It runs inside a Claude Skill.

Download the Skill once.

And anytime you want to check who owns a stock ask claude and he will:

1. Find the serious investors who own it (filtering out index funds and sub 2% positions )

2. Pull direct quotes from their letters, decks, and interviews

3. Map where they agree, where they split, and what’s worth researching next

You get an interactive web page like this one for Uber:

How to use it

Step 1: Install the Skill once.

• Download the Skill file (link below)

Read more

Here’s a simple example.

These are 2 sentences from Microsoft’s 10-Ks, 12 months apart:

• July 2024: “Intelligent Cloud revenue: $105,362 million.”

• July 2025: “Intelligent Cloud revenue: $87,464 million.”

The disclosure was a footnote.

But suddenly, $18 billion disappeared from Intelligent Cloud.

And before that change, some analysts were using those numbers to support the idea that Microsoft’s cloud business was bigger than AWS.

To be clear: this doesn’t mean Microsoft is “bad” or hiding something.

This is normal.

The point is simple:

Small changes in annual reports can change how investors see a business.

And catching all of those changes manually is extremely hard.

That’s where AI becomes interesting.

I built a Claude skill that compares years of filings side by side to find:

• accounting changes

• segments that moved

• KPIs that disappeared

• metrics that changed definition

• and shifts in the business story over time

Download the skill, install it once, and run it on any stock you follow.

In this video, I’m sharing the output using Microsoft as the example.

Subscribe now

How this claude skill turns years of filings into a clear business evolution map:

We will use skills inside Claude.

The idea is simple:

Make claude compare years of filings side by side and track what quietly changed.

How it works:

1/Download my Skill file.

2/Upload it once into Claude.

3/Type the stock name.

4/Claude creates an interactive web page that shows:

• where KPIs disappeared

• where definitions changed

• what changed in the reporting

• where useful lives got extended

• where acquisitions inflated growth

• what deserves a deeper read and analysis

Create Your Own Business Evolution Map in Minutes

Step 1: Use Claude Cowork

We’re building this inside Claude Cowork.

It’s the desktop version of Claude that can access files on your computer, run workflows across many filings.

Why Cowork instead of normal chat?

Normal Claude chat is great when you don’t need to read lots of precise files.

But ,here we want Claude to work across:

• Earnings transcripts

• 10 years of annual reports

• Multi-document comparisons

That needs a proper research environment.

That’s what Cowork gives you.

Your documents stay organized in folders on your computer.

Claude can:

• Open files automatically

• Pull the important information

• Run the workflow step by step

• Save the outputs directly

Instal the claude app and start using it

1. Open the official Claude website

2. Download Claude Cowork

3. Install the app

4. Log into your Claude account

5. Open Cowork

6. Start a new chat

7. Go to Step 2

Step 2: Group all the official filings into one folder

• Pick the company you want to analyze.

• Create a folder on your desktop named after the ticker

You need the last 5–7 years of:

• 10-K annual reports for US companies

• 20-F or equivalent annual reports for non-US companies

This is the raw material.

But you don’t need to collect everything manually.

You can do it yourself for fun…

If your definition of fun is opening 47 tabs and downloading PDFs.

I’d rather let Claude handle that part.

So I built a Filing Collector skill.

You give Claude:

• the ticker

• the number of years you want

And it builds the folder for you, instead of spending 30 minutes downloading documents one by one.

Step 3: Run the Business Evolution Map

• Now open Claude Cowork.

• Start a new chat.

• Give Claude access to the folder you created in Step 2.

Then:

• Click “+”

• Select Business Evolution Map

• Type the company name

• Run the skill

Wait a few minutes.

You’ll get an interactive web page with:

• what quietly changed in the reporting :disappearing KPIs, accounting changes, segment redefinitions

• what improvements were truly real :real business improvement vs accounting, acquisitions, buybacks, or cycle effects

• what actually drove the business changes: the main reasons revenue, margins, or cash flow changed over time

  

Upload the skill once. Use it forever.

Download this file.

Inside, you’ll find 2 Claude Skills:

1. Filing Collector : downloads all company filings automatically

2. Business Evolution Map : reads years of filings side by side and maps what really changed in the business

Read more

“Just buy exceptional businesses.”

Sounds easy when you hear it like that..

it’s look like you need only to:

• Open any screener.

• Sort companies by returns on capital…

• buy the top names…

• and wait.

But reality doesn’t work like that.

A 30% ROIC business is a target.

If the moat is weak, competitors arrive.
Margins compress.
and returns normalize.

We’ve seen it many times…

The real challenge is not reading the numbers.

• It’s understanding why the economics are strong

• whether they are actually protected

• and what could quietly destroy them over the next 5–10 years.

That’s where AI became extremely powerful.

Because AI is very good at:
• Gathering scattered information fast
• Mapping competitors and substitutes
• Stress-testing assumptions
• Simulating competitive reactions
• Generating scenarios you may not think about
• Connecting weak signals across an industry

In other words:

AI helps move the analysis from:

“this business looks exceptional today”

to

“what could stop it from staying exceptional?”

In this article, I’ll give you the exact prompt I use to pressure-test whether a “great business” is actually durable.

Watch this video to see what the output looks like and how to read it:

Subscribe now

How I Pressure-Test “Exceptional Businesses” With AI:

I’m not using a Claude Skill for this.

Because I don’t want to overcomplicate the workflow.

For this use case, one detailed prompt is enough.

The key is to run it inside Deep Research mode.

Why?

• Because I want the LLM to gather fresh data…

• read filings…

• compare competitors…

• pull industry signals…

It’s a research task so i will run a Deep Research inside Gemini

But Mostapha, why not Claude ?

You can use Claude too.

Claude is very strong, and honestly not far behind.

But for this specific workflow, I prefer Gemini because it is especially good at going out, gathering sources, and building a detailed research report from fresh information.

That said, don’t overthink the tool.

Use the one you already pay for.

I have the choice because I pay for all of them…

The real asset is the set of questions inside the prompt and the structure it forces the model to follow.

You are not asking:

“Is this a good company?”

You are asking:

• Why are returns high today?

• Why hasn’t competition destroyed them?

• Can new invested capital still earn high returns ?

• What could push the business back toward average in next 5 years?

That’s the value.

How to use it :

• Go to Gemini: Open Gemini and choose Deep Research mode.

• Use Thinking model

• Paste the prompt:Replace {Insert Company} with the company you want to test.

Read more

A friend tells you:

“ it’s a great business.”

It’s in an industry you’ve never touched.

You tell yourself:

“I’ll figure it out.”

So you do what any serious investor does.

You open the annual report.

“TPV growth…”
“Take rate compression…”

Weird jargon.
Bad explanations..

You skip it.

A year later, the stock is up 35%.

You tell yourself:

“It was outside my circle of competence.”

But it wasn’t.

You just didn’t have someone to explain the basics to you.

At 20, Warren Buffett took a train to Washington, D.C. to understand insurance.

He showed up at GEICO’s office on a Saturday.

He met an executive and asked questions for hours.

By the end, insurance clicked for him.

That understanding stayed with him for life…

The good news is that we’re in 2026.

And we have AI:

In this article, I’m sharing my Claude Skill file.

• You upload it once.

• You type the industry you want to learn.

• Claude creates an interactive guide that helps you get the basics fast, so annual reports stop feeling like a foreign language.

Subscribe now

How this Claude Skill helps you learn any industry 10x faster:

Instead of jumping between scattered notes and reports, everything is grouped in one place.

The Skill does this by creating one interactive learning page.

Inside, you get the full learning path:

1. The jargon explained in plain English

2. A clear 1-page summary of how the industry works

3. A deeper report that breaks down the key drivers and economics

4. A short quiz to test your understanding and reinforce what matters

5. Clear next steps on what to read, what to analyze, and how to go deeper

Nothing explains it better than seeing it in action.

Here’s a video where I run the skill live:

What’s inside the Skill

it‘s 1 ZIP file to download and upload into Claude.

But this is not one prompt.

It’s a structured workflow built from how I actually learn a new industry:

1. SKILL.md
This is the playbook.
It tells Claude what to do, in what order, and when each step runs.

2. The reference files
This is the core.

Each file is a tested prompt from my investing process:

• one to decode the jargon

• one to map supply, demand, and cycles

• one to structure the final learning output

Claude runs everything in sequence.

How to use it :

step 1: install the skill once, use it forover

• Download this file:
  

Read more

I don’t.

This is what my investing research process with AI usually looks like:

1. Understand the business:
AI helps me build an of how the company makes money and what drives economics.

2. Decide if it deserves deeper work:
After the overview, I decide if this stock is worth going deeper or not.

3. Read the annual report properly:
AI helps me go beyond the story and into the real disclosures, footnotes, and accounting.

4. Map the risks before conviction:
While I read the report, AI helps me build the downside map in parallel:

• what already looks fragile

• which disclosures deserve a closer read

• what questions I still need answered before conviction forms
  

5. Build the bull thesis :AI helps me turn the research into a clear upside case.

6. Stress-test it hard :AI helps me challenge my own thesis before I trust it.

This article is about step 4.

I built a Claude Skill called Stock Risk Auditor.

You run it with one command.

Claude then spends ~10 minutes doing the hard work in the background.

And let’s be honest: that’s a much better use of AI than asking it for “the next 10x stock.”

The output is a full Stock Risk Audit. Not a recycled “risk factors” section.

It gives you:

• the top risks ranked by importance across the business, the balance sheet, and the external environment

• a final risk label (Low / Moderate / Elevated)

In this article, I’ll show you how it works first.

Then you can take the skill, drop it into Claude, and use it in your next stock analysis knowing exactly what it’s doing.

Let’s dive in:

Subscribe now

How the Stock Risk Audit Works:

If you’ve never used a Claude Skill before, don’t worry.

A Claude Skill is basically a saved workflow inside Claude.

Instead of rewriting the same prompts every time, you install it once and run it when you need it.

That’s exactly what I’m giving you in this article.

How to use it :

1. Open Claude
   Claude Web is enough.
   You do not need Claude Desktop or Claude Code.

2. Start a new chat

3. Click the “+” button and select the skill
   Choose the skill from your saved skills.
   (You’ll need to install it first by uploading my file, but I cover that at the end of this article.)

   

4. Give it the stock name or ticker
   For example:CrowdStrike

Wait 10 minutes( Go do something else, Claude doesn’t need emotional support)

Result: a 7–8 page Stock Risk Audit, structured the way I designed it inside the skill.

My favorite part of the report is the final section: Next Deep-Dive Questions.

For CrowdStrike for exemple, one question was:

Can CrowdStrike keep charging premium prices if Microsoft makes Defender “good enough” inside Windows?

That’s useful.

Because the report doesn’t just tell you “there is risk.”

It tells you where to investigate next.

But Mostapha, how do I know that this is not just AI slop in a nice wrapper?

Fair question.

I’ve been using AI for investing for more than a year.

And from the outside, it’s hard to tell the difference between:

• a random prompt from someone who never seriously analyzed a stock

• and a real workflow built by an investor, tested across multiple stocks.

The difference is the structure behind it:

This is not one giant prompt asking Claude to “find risks.”

It’s a small research system inside Claude:

1. One main instruction file :It tells Claude the job, the rules, the ranking logic, and the final memo format.

2. Three tested investing prompts: These are prompts I had already refined and tested for 8+ months in my investing process.

• Business risk: what could weaken the operating engine

• Financial risk: what could stress cash flow, dilution, or the balance sheet

• Structural / external risk: what outside forces could change the economics

3. One synthesis step
Claude merges the three passes into one ranked Stock Risk Audit.

So the skill is not magic.

It is:

one main instruction file + 3 tested prompts + one final risk memo.

Now that you know how it works, let’s install the skill.

• Download this file:

Read more

Do you still read annual reports?

A question I got from a subscriber this morning.

Short answer: yes..

But not the same way I used to.

You might expect me to say, “Just let AI handle the whole thing.”

Nah. Not from me.

I believe in a hybrid investing process.

Let AI handle the mechanical work faster.
But the judgment still has to be yours

My investing process looks like this:

• Discovery = mostly AI ( detailed in This artcile )

• Annual report analysis = Hybrid AI + manual

• Decision-making = 100% manual

• Follow-up = Mostly AI, with selective manual review

In this article, I’ll show you 3 AI workflows I use to read annual reports faster and find the few details that can change how you see the business.

I ran it on Uber’s annual report.

It surfaced 3 things many investors would likely miss on the first read:

• Uber reported $10B of profit, but a big part came from tax benefits, not from the core business.

• Uber has a $1.8B UK tax issue tied to a court case that could hit earnings.

• Uber’s cash flow looked stronger in 2025 because it recorded more insurance cost than it actually paid in cash that year

That’s exactly twhat I want AI to flag in 5 minutes, so I can spend my time digging into the few points that actually matter.

How to use AI to find the buried details in annual reports:

There are 3 ways to use AI for the same job: read annual reports faster and catch the buried details that can change the investment case.

1) Using NotebookLM for a Fast Scan

Best for: getting a quick first pass and asking follow-up questions.

Trade-off: fast and useful and often the best first step before going deeper, but it can miss some buried details.

2) Gemini Prompt for a Deep Read

Best for: finding more of the buried details that NotebookLM can miss.

Trade-off: stronger output, but it works best when you give it a clear prompt and a manageable filing

3) Claude Skill for a Structured Review

Best for: getting the most reliable and repeatable version of that same job.

Trade-off: the strongest automated output, with a bit more setup upfront.

You can use any of the 3 depending on your experience with AI, your time, and how much depth you need.

But Mostapha which one should you use?

If you’re starting to use AI, start with NotebookLM.

Over time, you’ll find your own default.

Personally, I use all 3 depending on the stock, the complexity, and how deep I want to go.

Now let me show you exactly how to use each one.

Subscribe now

Level 1 :Using NotebookLM

NotebookLM is useful because it stays tied to the source you give it, which makes it great for annual reports.

It runs on Gemini, but in my experience, it’s still less powerful than using Gemini directly when you want deeper work.

Step 1: Add the annual report as a source

• In NotebookLM, click Search the web for new sources

• Type: “Uber latest annual report”

• NotebookLM will suggest a few sources

• Select the official annual report source

• Then click Import

You can also add it manually by uploading the annual report yourself.

Step 2: Surface the buried details with a custom prompt

This is the key part: we are using the power of NotebookLM’s source-based answers and combining it with a strong prompt to crate a rport that shows the details most people miss.

• Go to Reports,

• Choose Create Your Own:This matters because it lets you use your own prompt and force a more useful structure, instead of relying on the default report templates.

Paste the prompt below.

This prompt is built to do 3 things:

• stop generic summarizing

• force focus on the highest-signal buried details

• turn the output into a usable investor memo

What the report flagged:

For Uber, it generated a 7-page report that looked like this:

highlighting things worth paying attention to like:

• reported profit was boosted by a large one-time non-cash tax benefit

• insurance costs increased, which is an important pressure point to watch

These are exactly the kinds of things I want AI to flag quickly: details that can materially change the investment case.

Paste this prompt to generate the custom report:

Read more

They put cow tissue inside the human body.

I said that out loud between sets to my wife.

She froze.

“Shhh… she’ll hear you.”

Our 3-year-old is in “I loves animals” periode right now.

I was very close to creating a family disaster.

“Thanks. Now finish your set.”

My wife said.

In last Year, AI transformed my gym sessions to my first filter for discovering new stocks.

But that’s only a step of my process.

In this article, I’ll show you how I use AI to find more stock ideas:

• The tools I use at each step

• The prompts I use to decide if it deserves deeper work

• And the exact process you can add to your own investing research.

  ---

The Highest-Leverage Step in Stock Research:

If you only take one AI investing use case from me, make it this one:

Use AI to understand a business fast enough to decide if it deserves a real deep dive

This first filter is where the leverage is.

You don’t need to read the last 3 annual reports just to decide if a stock deserves your time.

well, you can…

But you’ll never see enough businesses to find the real winners.

And on the other side, you can’t just open a screener, look at P/E, revenue growth, and margins… and pretend you understand the business.

You need the basics:

• What does this company actually sell?

• Who buys and why?

• What drives growth?

• What’s the competitive edge if there is one?

That used to take a day of reading.

Now AI make that 10X faster ( with the right process)

How my AI first-pass workflow actually works

I already have more stock names than I can realistically analyze.

I keep them in a note app.

Stocks I’ve heard about.
Stocks I’ve seen on X.
Stocks I found in Substack posts, screens, podcasts, or random conversations.

Each step is built to get the most leverage out of AI with the least extra time.

Let me show you how I actually use it.

It happens in 3 steps:

1. Build Context in Parallel

I never start understanding a business at my desk.

If I did, I’d burn too much focused time too early.

So I use the time I already have.

Driving.
Walking.
Training.

That’s where I build the first layer of familiarity with a stock.

So when I finally sit down, I’m not starting cold.

I create an audio podcast from the a selected sources with the prompts I validated.

That way, I hear the business through the lens I actually care about, not generic ESG or macro talk.

During my latest Gym session, I did this with 2 names from my backlog:

• LeMaitre Vascular (the “cow tissue inside humans” company)

• MIPS (They sell a yellow safety layer inside helmets that prevent brain injury)

By the end of the workout, I already had a rough map of both businesses in my head.

Subscribe now

Is this fast ?

Let’s call it 0 extra minutes… and 2 business model snpashot already in my head.

Not bad I think..

2. Refresh the Context

When I go back to my computer.

Now the business is not new anymore.

I’ve already heard the story once.

So I open the 1-pager I already generated.

This page gives me the business model in the most optimized format for a first pass.

(I’ll show you how to create it at the end of the article.)

This is not where I discover the business.

I already did that with the podcast earlier.

By the time I sit down, some time has usually passed.

So this is just the quick refresh before I go deeper.

Time spent so far: ~5 minutes at the desk (after 0-minute parallel context building).

3. Read the Full Report

If the stock still looks interesting, I open the full report I already generated with AI that covers the exact points I want to undsertnat in a business.

So I can focus on the real question:

• What looks strong.

• What looks fragile.

• What might deserve a real deep dive.

This usually takes 10 to 12 minutes.

So in total you need only 15 to 20 minutes at my desk, I usually know if a stock deserves deeper work.

Often the answer is no.

That’s still a win.

• I learned somthing

• I killed a weak idea fast.

• And I kept the pipeline moving.

Now let me show you the exact tools and steps to have the same thing.

Note: Don’t read this and say “that’s nice,” and then never try it.

Whether you copy my process or not, you need something like this in your workflow.

Try it for one week, this will transform your investing process.

How to Build This 3-Step Workflow Yourself:

This workflow only needs 2 tools:

• Any LLM with Deep Research mode

• NotebookLM ( free is ok)

Quick reminder: Deep Research is non-negotiable.

The whole workflow depends on the quality of the reports.

That’s why I use Deep Research, not a normal chat prompt.

It’s the only reliable way to:

• build a real research plan

• scan hundreds of sources

• write the report in the exact format I want

But none of this works without a good, detailed, validated prompt.

I still use Gemini for this step because it still performs best here.

NotebookLM comes in Step 2.

Step 1: Generate the First-Pass Repports

Read more

“Mohnish Pabrai is a scam.”

My friend was dead serious !

I laughed.

No bro… even if he drops the “I was friends with Munger” line 10x per sentence.. he’s a legit investor.

Yes that’s the problem, my freind said:

“He talks like Munger and then buys Metallurgical coal stocks and offshore drillers.”

I laughed.

But I knew exactly what he meant.

My friend analyzes every stock like it should be a compounder.

His bear case is often:

“ROIC is only 15%… pass.”

But every investment thesis is different.

And different investments fail differently.

• A turnaround breaks when the business never turns.

• A compounder breaks when quality fades or you paid too much.

• A cyclical bear case is when peak earnings get mistaken for normal earnings.

What really matters is pattern recognition.

The kind that usually takes years in the market.

• Years of reading filings.

• Years of watching how stories break.

• Years of learning what actually kills returns.

Unless…

Now we have a machine that can compress years of pattern recognition into minutes.

Yes, that’s AI.

In this article, I’ll show you how to use Claude to challange any stock thesis, find the hidden weak points, and generate a bear case report.

By the end of this article, you’ll be able to:

• download a file

• upload it into Claude

• run it anytime you want to stress-test a thesis

But I don’t want you to use it like a black box.

Before you trust the output, you should understand the system behind it.

So let’s break down:

1. How this agent actually works

2. Why it thinks like an investor, not like a random AI prompt from the internet

The Real Cost of Borrowed Conviction:

Reading a great bull case is dangerous.

Because it can make you believe a thesis before you’ve done the work.

You read a strong write-up from your favorite investor.

And before you know the stock, you’re already seeing it through their lens.

That’s the big trap.

Now, Imaine this:

You read a bull case.

One click later, you get the counter-case.

Not a generic risk list.

A real attempt to break the thesis:

• where it’s weak

• what has to go right

• what could break it, and why

So before you believe the story…

you can test it.

Subscribe now

The 4-Layer Thesis Breaker for Claude

The full workflow is built inside Claude.

You give it a stock thesis.

Claude runs the process the same way every time.

• Layer 1: What kind of bet is this really?

• Layer 2: How does this type of stock usually break?

• Layer 3: What does the thesis really depend on?

• Layer 4: What does the evidence say?

That works because the system lives inside a Claude Skill.

Reminder:

A Claude Skill is a reusable workflow you can install inside Claude.

Under the hood, it is a packaged set of instructions, prompts, and reference files that tell Claude what to do, in what order, and how to format the output.

This is where I store the investing logic behind the system.

At the top is one main file: SKILL.md

Think of this as the control center.

It tells Claude:

• what output to produce

• what steps to run

• what order to follow

• and which files to load next

Then Claude opens the references folder.

This is where the investing logic, failure patterns, and research instructions are stored.

Let’s run this system together:

Here is how it works in practice:

• Install Claude Desktop (Cowork) on your computer

• Turn on Extended Thinking

• Use Opus 4.6

• Upload the thesis file:

  For example I’m using the Pershing Square Meta deck

• Trigger the skill
  Type: Run the Thesis Breaker Skill on this thesis

Now let’s break down what it is actually doing.

Share

Step 1: Identify the Investment Type

The first layer figures out what kind of investment this really is.

This matters more than most investors think.

Because if you frame the stock the wrong way, you build the wrong bear case.

This layer classifies the thesis as a:

• growth story

• turnaround

• cyclical

• serial acquirer

• asset play

• regulated / quasi-monopoly

• or a hybrid

Step 2: Find the Failure Mode

Once the system knows what kind of bet this is, it asks the right question:

Why does this type of investment usually fail?

For example:

• a great business bought at a terrible price

• growth that never becomes real economics

• a turnaround that is really structural decline

• peak margins mistaken for durable quality

• acquisition optics hiding weak returns

Claude uses my instructions to find the most likely way this specific thesis breaks.

Step 3: Rebuild the Bull Case

Before you can break a thesis, you need to know what the bull is actually betting on.

That is what this layer does.

It rebuilds the bull case from the real source material.

Then it strips the story down to the few assumptions that actually matter:

• growth stays strong

• margins keep improving

• returns on capital stay high

• the moat holds

• capital allocation stays smart

• the valuation still makes sense

This is critical.

Because most bull cases sound complex.

But most of them only depend on a few key beliefs.

And if one breaks, the whole thesis changes.

Step 4: Break the Assumptions

Now the system goes looking for evidence against those key beliefs.

Claude uses Deep Research to pull in more information from 50+ sources.

It starts with the official documents and trusted sources I validated in the skill reference files.

Then it turns all of that into one final output:

• what the bull is really betting on

• where the thesis is weakest

• what could break it

• what would prove the bear wrong

• and what to watch next

The Result

Once the skill finishes, you get 2 outputs:

• an interactive web page to explore the thesis

• a structured 8 pages bear-case report

Install the Skill

1. Download the file attached below:

Read more