“To a man with a hammer, everything looks like a nail.”

Read more

“That’s a lot of explanation. I’m more of a numbers guy.”

That’s what a portfolio manager with 20 years of experience told me while I was teaching him how to use Claude to get a complete overview of any business.

He continued:

“I like how it explains the business. But I’d prefer more financial data, historical numbers, and charts, with less text.”

And that got me thinking…

Not every investor approaches a business the same way.

Some prefer to start with the business story:

• How it makes money

• What drives the growth

• Why it beats competitors

Others prefer to let the numbers tell the story:

• How revenue and margins evolved

• Where profits and cash come from

• How effectively they invest capital

• What the stock might be worth now

But why choose between the two?

So I built a new version of my Business Overview Skill that combines both.

It goes beyond explaining the business, adding:

• Years of financial history with charts and tables

• Capital allocation analysis to see what past investments delivered

• A rough valuation to assess whether the stock deserves a closer look

All in one structured report.

The goal?

Go from “I know nothing about this company” to “I understand how this business works and whether it’s worth researching further.”

Let me show you what it looks like.

See It in Action

Here’s what the new Business Overview Skill produced when I ran it on Amazon:

How to get the same report for any company:

You don’t need to build anything from scratch or write complex prompts.

I’ve already built the research framework and packaged it into a reusable Claude Skill.

All you need to do is:

1. Install the Skill in Claude.

2. Enter the company you want to analyze.

3. Let Claude run the research and generate your report.

Step 1: Download the business overview skill

Read more

“Why is our most expensive machine not running?”

Read more

I know, you’ve probably heard that a thousand times…

Every week, there’s something new.

But over time, one thing has become clear to me:

The tools keep changing. The principles behind good investing research don’t.

That’s why I’ve built a research process that evolves with AI, instead of starting from scratch every time a new model comes out.

Today, I want to share the 3 building blocks behind that process.

I’ll show you:

• Why each one matters.

• How to use them correctly.

• And how they all work together.

The best part?

These building blocks don’t depend on Claude, ChatGPT, Gemini, or any specific AI provider.

You can use them in your research system, no matter which AI tool comes next.

And this isn’t just theory.

These are the principles I use in my own investment research, refined through my work with family offices and private investors.

Let’s get into it.

The 3 essentials of AI stock research (Regardless of the tool)

Read more

How specific their questions are when using AI.

That’s it.

You may be thinking:

My questions are already specific.

Let me tell you a secret: they probably aren’t that specific.

Specificity has levels.

And that difference can take AI from random answers to real research.

Why?

Because:

The deeper you go, the fewer decisions you leave to AI.

• You decide what to research.

• What information matters.

• How to analyze it.

• And what a useful answer looks like.

This is the principle behind almost every investing prompt and Skill I build.

I call it the 3-Layer Question Framework.

This is what I use to build my prompts and Skills.

A Skill can take me 8–10 hours to build.

But it always starts with this framework.

Let me show you how I use it:

The 3 layers of a great AI question:

Let’s get practical.

Last week, I shared the Financial History Reader Skill.

You can use it to turn 10 years of filings into a clear explanation of how a business evolved, and what actually drove revenue, margins, and cash flow.

It’s a huge research machine.

But underneath, it is built on the same 3-layer structure:

1. Outcome question: What exactly am I trying to understand?

2. Sub-questions: What do I need to answer to understand it?

3. Answer specification: What does a good answer to each question require?

Subscribe now

Here’s how to apply this 3-layer framework to any investing research question:

Let’s start with the kind of question most people would ask:

Analyze this company’s last 10 years of financials.

Think about how many decisions you just left to AI.

What should it focus on?

• Revenue?

• Margins?

• Which years matter most?

• How should it determine what caused a change?

• Should it trust management’s explanation?

• What counts as enough evidence?

• What should the final report look like?

You asked one question.

But underneath it, there are dozens of decisions AI now has to make for you.

So I start going deeper.

Layer 1: Outcome question

The first question is:

What exactly am I trying to understand?

For the Financial History Reader, the goal was not:

Analyze 10 years of financial statements.

I want to answer something much more precise:

What drove this business’s revenue, margins, and cash flow over the last 10 years, and how did its economics change over time, so I can decide whether it deserves deeper research?

Now the Skill has a job.

Everything it does should help answer that question.

But this outcome question is still far too big to answer directly.

So we go one level deeper.

Layer 2: Sub-questions:

This is where investing experience really comes into play.

Now I ask myself:

What subs questions do I need answered to understand the outcome?

For the Financial History Reader, that means identifying the financial and operating questions needed to explain each year:

• Revenue: Was growth driven by price, volume, mix, M&A, FX, or expansion?
  

• Segments: Which segment created the incremental revenue and profit?
  

• Margins: Which cost lines moved, what caused it, was it structural or temporary?

• Balance sheet: What do changes in debt, working capital, goodwill, or share count tell me about the business?

• Plus a handful of other questions…

But even this still leaves decisions to AI.

That’s where Layer 3 begins.

Layer 3: Answer specification

This is where research discipline comes into play.

Now I ask myself:

What would I require before accepting AI’s answer to each question?

For the Financial History Reader, I define:

• Where to look: filings, earnings releases, calls, and structured financial data.

• What to check: restatements, changing definitions, and whether the numbers are actually comparable.

• What to test: whether management’s explanation is supported by the numbers.

• What to distinguish: reported facts, calculations, and AI inference.

• What business data to use: price, volume, customers, units, utilisation, or whatever actually explains the financial change.

• How I want the report: short year-by-year cards, more detail only on important years, then the few mechanisms that explain the decade.

This is how you turn AI from guessing what to do into following a clear research process step by step.

Share

Final thoughts

I know that this takes time…

But the more clearly you define it beforehand, the less AI has to guess, and the better the research gets.

See you next week,
Mostapha

P.S. If you don’t want to build all of this yourself, paid members get access to my ready-to-use investing Skills, including the Financial History Reader.

Become a Member

How did this business evolve over the last 10 years and what drove the changes in revenue, margins, and cash flow?

To answer it, you had to figure out:

1. Where growth really came from :organic growth, acquisitions, pricing, volume?

2. Why margins changed: Operating leverage, accounting, or temporary effects.

3. Where the cash actually went : reinvestment, acquisitions, buybacks, or dilution.

It means digging through 10 years of filings, rebuilding the financial history, and turning it all into one clear memo.

Now you can get that first pass with one command in Claude.

In this article, I’ll show you how to build this workflow once, then reuse it every time you start researching a new stock.

Subscribe now

Turn 10 years of financials into one clear story

Here’s what the output looks like in practice:

With one command inside Claude, ran on Netflix.

Claude generate a report covering years of financial history that explains:

• why EBIT margin expanded from 4.3% to 29.5%

• why the first positive FCF year was partly a timing effect

• why Netflix could report rising profits while still burning cash

• which years actually changed the story, and which were just temporary noise

So next time you research a business, let Claude do the digging so you can spend more time thinking about whether the business is actually worth owning.

How to Run This on Any Stock:

Read more

Watch the replay

Get more from Compound With AI in the Substack app

Available for iOS and Android

Get the app

“3 more kids and we might finally have this parenting thing figured out”

That’s what I told my wife 10 days after our second child was born.

She didn’t seem very excited about the idea of 3 more..

But the joke wasn’t completely wrong.

With our first child:

• Every problem felt new. Now we recognize things we’ve already seen before.

• Everything felt important. Now we know what actually deserves attention.

• We researched everything from scratch. Now we reuse what already worked and continue to learn.
  

At this point you may be thinking:

“Mostapha, I’m not here for parenting and life advice.”

Fair.

I’m definitely not launching Compound With Kids…

But the same lessons apply to AI.

After 18 months of using AI daily for investing, I learned what matters, and what workflow to use for each step.

That’s what this guide is about.

Helping you build that process faster, without repeating all the mistakes I made along the way.

If you’re starting with AI for investing, you only need to get 3 things right:

1. Choose the right AI.
   

2. Set it up correctly for investing.
   

3. Build a repeatable research process around it.
   

Get those three right, and you already have the foundation of a real AI investing process.

Subscribe now

1. Choose the right AI tool for the job

I get this question a lot:

Claude? ChatGPT? Gemini? And where does NotebookLM fit?

My answer is simple:

I don’t use one AI tool for everything. I choose based on the job.

Today, my default looks like this:

1.Starting a new company or industry: Gemini Deep Research + NotebookLM

• I use them to get up to speed fast.

• Gemini helps me build the first overview across many sources.

• I use Notebook to ask follow-up questions and create an Audio Overview podcast.

2.Going deeper on a company: Claude

• This is where I work with years of filings, spreadsheets, notes, and more complex research tasks.

• Claude is currently my preferred tool for this kind of deeper, file-heavy work.

3.Following a stock and running repeatable workflows: Claude

• Once the deep dive is done, I don’t want to rebuild the research every quarter.

• I keep the company work together and reuse the same workflows for earnings, thesis checks, risks, and follow-up research.

If that already sounds like too many tools, don’t overthink it.

You can use Claude for almost the entire process.

So today, my recommendation is simple:

Start with Claude. And especially Claude Cowork.

Here’s what that looks like in practice:

Now the important question becomes:

How should you actually use Cowork for investing?

Read more

AI solves a different problem at each stage of the investing process.

• For New ideas: AI helps research more companies, faster, so I can see more opportunities.

• Going deeper: AI helps understand the business better and surface things I may have missed manually.

• Building the thesis: AI will challenge my assumptions and find what could prove me wrong.

• After I buy: AI will track earnings, new risks, and what materially changed in the thesis.

Here is how I use AI at each step.

Subscribe now

The 4-Step AI Investing Process:

1. Overview: Understand more businesses, faster

Let’s say someone sends me a stock I have never looked at before.

I do not start by reading the entire annual report.

First, I want a fast answer to a simpler question:

Is this company interesting enough to deserve more of my time?

I use AI to understand things like:

• How does the company make money?

• Who are the customers?

• What drives revenue growth?

• Where do margins come from?

• How does the industry work?

• Who are the main competitors?

• Is the business cyclical?

• Does it need a lot of capital to grow?

Here is a video of an example with Claude:

The goal is not to understand everything.

It is to understand enough, quickly, to decide whether the company deserves deeper work.

That lets me look at more businesses without spending hours on every idea.

2. Deep Dive: let AI do the heavy analytical work

If the company still looks interesting, I go deeper.

Now I am no longer trying to understand the broad story.

I want to know:

What does the evidence actually show?

This is where I spend time in:

• annual reports

• financial statements

• transcripts

• proxy statements

• investor presentations

• historical disclosures

And this is where AI becomes especially useful.

For example, in this video I ran my Business Evolution Map Skill on Microsoft.

Instead of reading years of annual reports one by one, Claude compared the filings and looked for things like:

• KPIs or disclosures that appeared or disappeared

• changes in how management describes the business

• shifts in risks and segment reporting

• accounting changes

• changes in useful-life assumptions

AI helps me find what I might have missed manually.

3. Building the thesis: use AI to challenge yourself

This is where AI should push back my assumptions.

For example, I give Claude my thesis and run a Skill that asks it to test things like:

• whether my growth assumptions are realistic

• whether the margin expansion is supported by history

• what has to be true for my expected return to work

• which risks could permanently damage the thesis

• what a smart short seller would attack first

The goal is simple:

Find the weak points before the market does.

4. After I buy: track what changed

Once I own the stock, I do not want to restart the research every quarter.

I already know the business.

I already have a thesis.

So after earnings, I want AI to answer a much narrower question:

What changed relative to what I already believed?

For example, in this Uber video, I run my Earnings Update Engine inside Claude.

It pulls the new earnings data, compares it with the previous quarters and my existing research, then checks:

• what changed in the key KPIs

• whether guidance improved or weakened

• whether new risks appeared

• whether management credibility changed

• whether the thesis is stronger or weaker

How to build your own process

1. Start with one company you know well.

2. Use AI for one part of your research.

3. Keep what saves time or improves the analysis.

4. Turn it into a workflow you can reuse.

5. Repeat for the rest of your process.

Over time, AI stops being random prompts and becomes part of your investing system.

See you,
Mostapha

P.S. Want to build a process like this without starting from zero?

Join as a paid member and get my full AI Investing Skill & Prompt Library, including the workflows I use for business overviews, deep dives, thesis testing, and earnings updates.

Your favorite investing newsletter just published a new stock idea.

You open it.

Start reading:

1. The business looks good.

2. The numbers make sense.

3. The upside looks attractive.

A few minutes later, you’re checking the stock price.

But before you go further, something bothers you.

• Is that growth assumption realistic?

• Can margins really go that high?

• Did the author miss something?

So you open Claude to check the growth assumptions, profit margins, and math behind the stock pitch.

Here’s what that looks like with a real example :

I picked a stock pitch from Value Investors Club.

The author made a case for roughly 16% annual returns.

Here’s what Claude flagged:

• A math issue :Fixing it brought estimated annual returns to 15%.
  

• A recovery assumption to check: the model needed stronger sales growth in 2027, while management expected its markets to stay flat.

• A margin goal to test: the pitch assumed an 11% adjusted EBITDA margin. the business had only reached that level in 2021 and 2022, though management outlined improvements that could help it get there again.

Claude then went claim by claim, marking each as holds up, overstated, or can’t be checked.

Subscribe now

By the end of this article, you’ll have the skill and the steps to run this check on any stock pitch, including your own.

Let’s set it up:

Step 1: Give Claude a stock pitch to check

Read more

And since I started using AI in 2025 I’ve compounded at 19% a year.

Did Claude and Gemini cause those returns?

I’d be fooling myself if I said yes…

But here’s what I can say with confidence:

AI has made me a better investor, and I sleep better at night because of it:

1. I’ve researched more companies and industries than ever before.

2. I know the stocks I own today in more depth than I ever did before.

3. I’ve rejected more investment ideas because I found risks much earlier in the process

4. I’ve gone much deeper into the details, edge cases, and unanswered questions I used to leave unexplored.

That matters far more to me than pretending AI added a few percentage points to my returns.

Since 2025, I’ve run 3,500+ prompts and AI skills for investing.

Over time, I noticed a pattern: the research was consistently better when I followed a few simple rules.

Those became 7 operating rules I try not to break.

Here they are:

1. AI is the analyst. You are the investor.

This is the most important rule.

And yes, I know what some of you are thinking:

“Mostapha, we know this.”

It sounds obvious.

But in practice, the line between analysis and judgment gets blurry very fast with AI.

Some questions are ultimately mine to answer:

• Has management earned the right to reinvest more capital?

• Is the expected return attractive enough given the uncertainty?

• Is this growth durable, or am I extrapolating a temporary tailwind?

I use AI to research the evidence to answer this questions.

let’s take growth durability.

I will ask AI to go through years of filings and show me:

• price vs. volume vs. mix

• organic vs. acquired growth

• structural vs. cyclical drivers

• market-share gains vs. market growth

• performance through previous slowdowns

• what management expected vs. what actually happened

That is analysis.

But how much of that growth am I willing to underwrite for the next five years? That’s my judgment.

2. Start with questions, not prompts.

Every time I build a prompt or a Skill, I start with one question:

What exactly do I need to know?

For example:

• How does this business really make money?

• Why are margins higher than peers?

• What drives returns on capital?

• What could destroy the thesis?

Then I ask myself:

If I were researching this without AI, how would I answer it?

1. Which filings would I read?

2. Which numbers would I compare?

3. Which periods matter?

4. Which competitors would I look at?

5. What evidence would actually answer the question?

Only then do I turn that research process into a prompt or Skill.

The quality of the research starts with the quality of the questions.

3. Control the evidence.

Once I know the question, the next thing I want to fix is :

what AI is allowed to use to answer it.

If I’m researching capital allocation, I want the proxy, filings, buyback history, and M&A record.

Because if the source is weak, the analysis is weak no matter how good the model is.

If I’m studying margins, I want years of reported numbers and management commentary.

If I’m tracking what changed, I want the actual filings side by side.

I don’t want AI building the answer from random articles, summaries, or whatever it already “knows.”

The rule is simple:

I choose the evidence. AI analyzes it.

4. Research first, opinion last.

I try not to ask AI for an opinion before the research is done.

If I start with:

“Is this a great business?”

the model can form a story first, then pull facts that fit it.

So I separate the 2 steps.

1. Research first: collect evidence, compare periods, extract numbers, find disclosures, answer specific questions.

2. Opinion last: decide what matters, what I believe, and whether the evidence is strong enough.

The order matters.

First build the evidence. Then build the view.

5. Explain the why, not just the what.

This is one of the easiest traps to fall into with AI.

You ask why a company could earn more in a few years.

The answer sounds great..

Then you look closer and realize it never actually explained how.

you’ll read :

“Margins should improve.”

0 added value for me !

I want to know why.

• Price?

• Volume?

• Mix?

• Lower costs?

• Operating leverage?

For example:

Higher pricing + fixed-cost leverage, partly offset by wage inflation → margin +180 bps.

Now I have something I can test.

6. Hire AI as your short seller.

AI becomes more useful once I start liking a company.

Because that’s when confirmation bias becomes dangerous.

So I flip the role.

Instead of asking AI to strengthen my thesis, I ask it to attack it:

• Find the evidence I’m ignoring.

• Build the bear case.

• Identify the assumptions carrying most of the thesis.

• Tell me what would need to happen for me to be wrong.

• Compare what I assume with what management is actually delivering.

• Show me the strongest argument against owning the stock.

I want assumptions that can be tested.

I want numbers I can monitor.

I want conditions that would force me to change my mind.

Because a thesis that cannot be wrong is not really a thesis.

It’s a story (a dangerous one).

7. Compress work, not thinking.

This is the point of the whole process.

Of course it makes me faster.

I can pull numbers from filings, compare several years, check competitors, track earnings changes, or find one detail buried in 300 pages much faster than before.

But I don’t really care about being faster just for the sake of it.

I care about what that speed gives me back:

• More time to ask one more question.

• More time to just sit with the business and think.

• More time to check the assumption I’m least comfortable with.

That’s also why I keep turning repeated work into Skills, Projects,and templates.

I don’t want to rebuild the same research every time.

less time doing the work around the thinking, more time actually thinking.

Recap

If you’ve been reading me for a while, you know I’m not trying to turn investing into an automated process.

I still want to do the hard part myself.

I want to decide what matters.
I want to make the judgment.
I want to live with the consequences if I’m wrong.

AI just helps me do the work around that much better.

So these are the 7 rules I keep coming back to:

1. AI is the analyst. You are the investor.
2. Start with questions, not prompts.
3. Control the evidence.
4. Research first, opinion last.
5. Explain the why, not just the what.
6. Hire AI as your short seller.
7. Compress work, not thinking.

If this was useful, share it with one investor who’s trying to figure out how to actually use AI for Investing.

Share

See you next week,
Mostapha

P.S. I already spent the time building and testing the AI investing workflows.

Join Compound With AI Premium and use the ready to use prompts, Skills, and research systems on your next stock.

Subscribe now

Yes. We’re getting somewhere !

The industry tailwinds look real.

Now,you have 2 annual reports open side by side.

Both companies look attractive.

Which is annoying !

Because now you have to decide:

Which one is worth another 3 hours of your time?

I taught Claude how to compare any 2 stocks in the same industry the way I want to compare them:

• Where growth comes from

• Who has the better cost engine

• Who has more competitive power

Then Claude puts both companies side by side and shows me:

1. Where each one is stronger

2. What could change that view

Here’s how to use it:

Which Business Is Actually Better?

When I compare 2 businesses, the better one is the one that can:

• Grow for longer.

• Defend its advantage.

• Turn that growth into more profit.

Take Zoetis and Virbac.

2 animal health companies at very different scales.

Let’s use Claude on this example to see where each business is stronger:

1. Go to Claude :no need for Cowork.

Subscribe now

2. Call Peer Duel: a Skill I built with a set of instructions designed specifically for comparing 2 businesse in same industry

3. Name the 2 stocks you want to compare.

Wait a couple of minutes and you will have in 1 report:

• Growth map: where growth comes from by product and geography

• Power map: pricing power, customer relationships, competitors, and suppliers

• Cost engine: COGS, R&D, SG&A, and margins

• Vulnerabilities: what could break the thesis for each company

• Final call: where each company is stronger and which one deserves the deeper dive

Here’s a snapshot from the report comparing Zoetis and Virbac:

But Mostapha, why should I trust this?

Fair question.

I spent hours building and testing the Skill before sharing it.

But that is not the reason you should trust the output.

The Skill structure is the secret.

It forces Claude to:

• Use primary sources: filings, annual reports, transcripts, regulators

• Trace every important number back to a source

• Normalize currencies and reporting differences before comparing

• Check what changed recently: guidance, deals, management changes

• Break the comparison into 3 levers: growth, power, and cost engine

I did give claude a repeatable, clear framework to follow .

That’s always the secret:

1. The human experience builds the framework.

2. AI brings the speed and depth of the excution.

3. The humain test, validate, and improve

Download the Peer Duel Skill:

Read more

I was explaining how AI transformed the first step of my process:

The Overview phase.

This is where I try to understand the basics of a company and its industry before going deeper.

I needed an example…

But using a stock I already knew would be dishonest.

Then I remembered Martin Marietta.

I had recently seen on X that Chris Hohn bought the stock.

One participant said:

I know this business.

I knew nothing about the company.

I said: great exemple !

So I opened Claude and showed them exactly what I would do starting from zero.

I continued the research after the workshop.

And within a couple of hours, I went from:

"I have no idea how this business works."

to:

"Okay. I get the business model"

Here’s exactly how I did it with Martin Marietta :

The 2 steps to understand a new stock:

When I know nothing about a stock, I call 2 friends:

Friend #1 teaches me the industry:

• How the industry works

• what drives the economics

• and translates the weird terms into plain English.

Friend #2 explains the company:

He reads the filings and gives me a short, clear explanation of:

• How it makes money

• Who its customers are

• What really drives the business

That’s what I will do with Claude!

But I don’t have to pay a salary.

And no one’s wife is asking:

“Who is Marietta, and why have you been talking about her for 2 hours?”

Step 1: Understand the industry

If I already know the industry, I skip this step.

But with Martin Marietta, I knew nothing about it…

So I opened Claude and I fired this question with my special skill Learn Any Industry:

A few minutes later, I had everything I needed to understand the industry:

Subscribe now

Claude gave me 3 parts:

1. The Industry language

For every important industry term, Claude explained:

• What it means

• Why it matters for investors

I woud be honest…

Before AI, this would have taken me hours.

And I still wouldn’t have ended up with something this clear.

But that’s only the first part.

2. The economics of the industry

The seconde part is a one page summary of what actually moves the industry:

• The top 3 demand drivers

• The top 3 supply drivers

At this point I got the industry language and the main drivers…

Now I was ready to go deeper.

3. The full industry report

Claude gave me a 6000 word report explaining the industry in detail.

For Martin Marietta’s industry, one of the most useful sections was the boom and bust analysis.

It showed me what happened during the 2006–2011 US construction crash, the Spanish bust, China’s cement decline, and the recent price-led cycle.

Why does this work?

You have every right to ask me:

Okay Mostapha, but why does this create something useful instead of a generic ChatGPT-style summary?

It’s not magic.

It comes from the way the Skill is structured.

I taught Claude exactly what an investor needs to understand about an industry.

Things like:

• What drives demand

• What limits supply

• How pricing works

• What drives margins

• How the industry behaved in past cycles

That changes the output completely.

and after bulding it ,I tested this Skill across 10+ industries to validate it.

You can download the Learn Any Industry Skill from the Skill Library here:

Read more

AI will improve your returns.

Not with some magic AI stock picks.. but because it improves the 3 things that drive investing returns:

More opportunities × Better picks × Smaller losses

Here’s how AI helps with each one:

Subscribe now

#1 AI cuts research time, so we can look at more stocks:

Toyota went from selling textile machines to the world’s largest carmaker, selling 11+ million vehicles a year.

One simple idea helped build this giant:

Cut the work that adds no value.

Let’s be honest: we spend a lot of time doing work that needs to be done, but doesn’t need us to do it.

Why should I read 300 pages just to understand how a business works… only to decide I don’t even want to own it?

We’ve all read a good report that helped us understand in 15 minutes what would have taken us hours alone.

That feeling is great, right?

With the right AI workflow, we can understand the basics of a business in minutes.

More on this in this article if you’re interested:

let’s continue, what about filings ?

Why should I manually download 10 years of annual reports, open them one by one, and search for what changed?

Claude can collect the filings, compare them, and show us:

• how the business changed over time

• what really drove the growth in the past

• which products or segments became more important

• how the company makes money today vs. five years ago

Hear me : the work still needs to be done, we just can do it 10X faster !

And that time matters.

That’s time we can spend finding new ideas, looking at more companies, and hunting for the next great stock.

More companies studied = more chances to find a great investment.

#2 AI helps us understand businesses better, so we can pick more winners.

This part is underrated.

If you’ve spent time in the markets, you know the best investments are not always obvious in the numbers.

If everything was already obvious in the numbers, everyone would already own it.

You need to go deeper:

• Why do customers stay?

• Why can margins keep growing?

• Why can this business keep winning for years?

• Why do competitors struggle to copy the same model?

In the past, getting good answers meant finding an industry expert who had spent years learning the business.

Thanks to some crazy folks in Silicon Valley, we can now get years of expertise from one tool for few $$ a month.

And Deeper understanding = better chances of picking the real winners.

#3 AI helps find hidden risks, so we can avoid big losses.

This matters just as much as finding winners.

AI can be the partner that:

• challenges our thesis

• asks the hard questions

• checks years of reports

• looks for what we may have missed

And then ruins our confidence with:

“Nice thesis. But what about this risk on page 215?”

Tha’s annoying ?

Yes!

But is it useful ? 100%

That is exactly what I want AI to do

Better questions = fewer blind spots = fewer big losses.

More on how to bulid this in this article:

So what am I begging you to do?

Just start.

1. Pick one tool.

• Gemini if you mainly use deep research prompts.

• Claude if you want to go further with Skills and repeatable workflows.

2. Start with a stock you already know very well
This makes it much easier to see where AI is good, where it is wrong, and what questions get the best answers.

3.Test and learn:

Use a first Prompt or a skill

See what’s not working and delete it.

Keep what works and keep improving

4. Slowly build your AI process

in 2-3 monthes you’ll have your own AI investing process that helps you:

Find more opportunities × Pick better winners × Avoid bigger losses

See you next week,
Mostapha

Share

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