The One-Ticker Committee
Big funds make 6 experts argue before they buy a stock. Run that same argument on any stock in 15 minutes, free, with one Claude chat.
How it works: One stock + one dated fact → 6 experts argue → the Devil's Advocate attacks → Risk can veto → PASS, WATCH or CANDIDATE
READ FIRST: It never buys or sells. Most ideas get PASS or WATCH, and that's the point.
Free full guide (step by step, with 12 copy-paste prompts, daily routine and weekly review): milli-ai.com/free/hedge
Build the free starter version with Claude Code (20 minutes)
Want it running on your computer instead of in a chat? Paste one prompt and Claude Code builds a starter 6-role Hedge Fund Committee that debates any ticker and writes a one-page memo. It runs on pretend money or in read-only mode. It never places a trade or bet.
You need: Claude Code (needs a paid Claude plan), Python 3, and an Anthropic API key from console.anthropic.com (pay as you go, usually cents per run).
1. Install Claude Code (Mac/Linux terminal):
curl -fsSL https://claude.ai/install.sh | bash
Windows PowerShell: irm https://claude.ai/install.ps1 | iex
2. Make a folder and open Claude Code in it:
mkdir hedge-committee && cd hedge-committee
claude
3. Paste this build prompt:
Build me a beginner-friendly starter bot called hedge-committee in Python 3: a starter 6-role Hedge Fund Committee that debates any ticker and writes a one-page memo.
WHAT IT DOES
1. Command: python src/main.py --ticker AAPL. Pull 1 year of daily prices and basic company info with the free yfinance library.
2. Run 6 separate Claude calls, one per role: Macro, Fundamental, Technical, Devil's Advocate, Risk Manager (can veto), PM. Each role sees only the data plus the earlier roles' answers and replies as JSON: {"view","evidence":[..],"confidence"}.
3. The PM writes the final call: PASS, WATCH or CANDIDATE. A Risk veto forces PASS. Save the memo to memos/TICKER-DATE.md.
RULES FOR THE BUILD
4. Use the official Anthropic Python SDK. Put the model name in config.json. Read ANTHROPIC_API_KEY from .env with python-dotenv. Create .env.example with placeholders and add .env, data/ and logs/ to .gitignore. Never hardcode keys.
5. It never places real trades or bets. No broker or wallet code, no private keys.
6. Put every setting (limits, tickers, thresholds) in config.json so I can change them without touching code.
7. Add a --demo flag that runs the whole thing on made-up data with no internet, so I can test it first.
8. Handle errors and rate limits with a short wait and retry. If you are not sure an API endpoint or field exists, leave a clear TODO instead of guessing.
9. Write a README.md for a total beginner: install, add the key, run --demo, run for real, read the logs.
10. Keep it simple and well commented, under about 400 lines. When done, explain what you built and list anything you could not check.
4. Install and test:
pip install -r requirements.txt
cp .env.example .env
python src/main.py --demo
Add your key to .env with a text editor, then run it for real (the README shows the exact command).
Keep your key safe: never paste API keys into a chat, a screenshot or GitHub. Keep
.envin.gitignore.
Starter vs finished
| Starter (free, this prompt) | Finished (AI Desk) | |
|---|---|---|
| Works on your computer | ✅ | ✅ |
| Pulls filings, earnings and news with dates | ❌ | ✅ |
| Tested role prompts | ❌ | ✅ |
| Scorecard that tracks each role's accuracy | ❌ | ✅ |
| Weekly watchlist run | ❌ | ✅ |
| Tested by us, with setup support | ❌ | ✅ |
Troubleshooting
| Problem | Fix |
|---|---|
| It gives one long essay | Reply: "Answer as the 6 roles, then one call." |
| It says CANDIDATE every time | Tell the Devil's Advocate: "Find the strongest reason not to buy." |
| It makes up numbers | Give it your dated fact and say "use only facts I give you". |
Want the finished version?
The prompt above builds a starter. The finished, tested version (one-command install, plain setup steps, and help if you get stuck) is part of the Milli.ai AI Desk.
- Free full guide: milli-ai.com/free/hedge
- Finished bot: milli-ai.com
Educational only. Not financial advice. It never places trades for you. You make every decision.