A Practical Field Guide

Using Claude for Investing Research

How to get an AI research analyst running in your terminal in about fifteen minutes, and what to actually do with it once it is there. Written for investors, not engineers.

Maintained by Neil Patel · Last updated 2026-07-16 · Pricing shown is current as of July 2026 · Not investment advice.
Setup time
~15 min
one time, on your Mac or PC
Cost
$100/mo
Claude Max (recommended)
Coding required
None
you talk to it in plain English
Best models
Opus / Fable
set reasoning to xhigh

The one-paragraph version

Claude Code is Claude running in your terminal. Unlike a chat window, it can read files, pull financial data, run analyses, and save its work, all by you typing what you want in plain English. For research, that means a tireless junior analyst that reads every earnings transcript, builds screens you can re-run each quarter, stress-tests a thesis, and writes up memos. The path: subscribe to Claude Max ($100/mo), paste one install line into your terminal, switch it to Opus or Fable on xhigh, then start asking. The rest of this page walks each step.

01What this actually is

If you have only ever used the Claude chat app, this is the part worth reading slowly.

Most people meet Claude through the chat window at claude.ai. That is great for questions, but it cannot reach into your files or run anything. Claude Code is the same intelligence, living in your computer's terminal, where it can: it reads and writes documents, fetches data from the web and from data providers, runs calculations, and keeps a working folder of everything it produces.

For an investor, the mental model is simple. You have hired a sharp junior analyst who never sleeps, works only for you, and does exactly what you ask. You do not write code and you do not learn commands. You type things like "pull this company's last four calls and tell me what changed." It goes and does it, then hands you the answer and the file.

02Pick your plan

Claude Code is not on the free tier. You need a paid subscription, and the tier matters.

PlanPriceGood for
Free$0The chat app only. Does not include Claude Code.
Pro$20/moIncludes Claude Code. Fine for dipping a toe in, but you will ration yourself on heavier research.
Max Recommended$100/moThe sweet spot for real research: plenty of usage so you are never rationing, plus access to the most capable models. This is the tier to start on.

Start on Max. If you would rather test the water first, Pro works and you can upgrade in one click later. Sign up at claude.ai.

03Get it running

Four steps. You cannot break anything, and it is easy to remove if you ever want to.

  1. Subscribe. Go to claude.ai, make an account, and subscribe to Max (or Pro).
  2. Open your terminal. On a Mac, press Cmd + Space, type Terminal, and hit Enter. A plain black-and-white window opens. That is the terminal. On Windows, open PowerShell the same way from the Start menu.
  3. Install Claude Code. Copy this exact line, paste it into the terminal, and press Enter. Wait about a minute for it to finish.
    # macOS
    curl -fsSL https://claude.ai/install.sh | bash
    # Windows (PowerShell)
    irm https://claude.ai/install.ps1 | iex
  4. Start it. Type claude and press Enter. It opens your browser to log in. Use the same account you just subscribed with. That is it, you are in.

Optional but tidy

Before you run claude, make a folder for your research so its notes land in one place. Paste these one at a time:

mkdir -p ~/Desktop/research
cd ~/Desktop/research
claude

Prefer a window over a terminal?

There is also a Claude desktop app that runs the same thing in a normal app window. The terminal is worth the few extra minutes and is what most of this guide assumes, but the desktop app is a fine place to start if the black window feels intimidating.

04Make it smart

One setting does more for research quality than anything else.

Claude comes in several models, and it can also think harder or faster depending on how you set it. For investing work you want maximum intelligence, not speed. Once you are in, do two things:

That combination, a top model on xhigh, is what gives you the sharpest analysis. It is a little slower per answer, which is exactly the trade you want when you are pressure-testing an idea rather than firing off a quick lookup.

05What to actually ask it

The hardest part for most people is the blank page. Here are prompts that work. Copy one, swap in your names, and go.

Read the transcripts
"Pull [company]'s last four earnings call transcripts and tell me how management's language around [pricing / AI / demand] has shifted quarter over quarter. Quote the exact lines that changed."
Stress-test a thesis
"Here is my thesis on [ticker]. Argue the other side as hard as you can. What am I underweighting, and what would have to be true for me to be wrong?"
Build a screen you can re-run
"Build me a screen of sub-$5B software companies where revenue growth is re-accelerating. Rank them, show the numbers, and save it so I can re-run the same screen next quarter."
Interrogate a filing
"Read [company]'s latest 10-Q. Summarize the quarter in ten bullets, then flag anything that contradicts the bull case or looks like a change from prior filings."
Compare on valuation
"Compare valuation multiples across [tickers]. Show growth alongside the multiple and tell me which looks cheapest relative to how fast it is actually growing."

You do not have to get the prompt perfect. Ask, read the answer, then just say "go deeper on point three" or "now check that against the actual filing." It is a conversation, and it remembers the context.

06Level up with a data feed

Once the basics feel natural, this is the upgrade that makes it genuinely powerful.

Out of the box Claude can search the web, which is often enough. But the thing that turns it into a real research desk is a dedicated data feed. A good, inexpensive one is Financial Modeling Prep (FMP). For a modest monthly subscription you get an API key, a short string of characters, that lets Claude pull earnings transcripts, fundamentals, and estimates directly and reliably.

No rush on this. Get comfortable with the basics first, then add the key when you find yourself wanting cleaner data. Setting it up is a one-time, five-minute job.

07Use it well

A few ground rules so it makes you sharper instead of overconfident.

It is a research tool, not an oracle

08Where this goes

Once it is part of your routine, small automations compound.

After a few weeks people tend to build things they did not expect to. A running research hub that files every memo and screen in one searchable place. A short pre-market email each morning on each holding that flags anything relevant to the thesis. Screens that re-run themselves and ping you when a setup appears.

If you want to see what the finished output can look like, here is a full public research dossier built this way: coin.neilkpatel.com.

The honest pitch is this: it will not pick stocks for you, and you would not want it to. What it does is remove the grunt work between having a question and having an answer, so you spend your time on judgment instead of gathering. That is the whole game.