Milli.aiFree guides

The 7-Bot Trading Desk

Seven AI bots, one vote, and a risk bot that can veto anything. Run any stock idea past all seven in 15 minutes, free, and see how the automatic desk is built.

How it works: Your idea → 7 bots each check one thing → Risk can veto → 5 of 7 must agree → one clear ticket

READ FIRST: It never places an order. A "no" from the desk is a win: it saved you money.

Free full guide (step by step, with 12 copy-paste prompts, daily routine and weekly review): milli-ai.com/free/bots

Get the full free guide →

How it works

The finished version runs the same desk on its own, every hour the market is open:

Educational only. Not financial advice. One AI playing seven bots is still one AI, so check its facts.

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 7-Bot Desk: 7 bots vote, 5 of 7 must agree, and Risk can veto. 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 seven-bot-desk && cd seven-bot-desk
claude

3. Paste this build prompt:

Build me a beginner-friendly starter bot called seven-bot-desk in Python 3: a starter 7-Bot Desk: 7 bots vote, 5 of 7 must agree, and Risk can veto.

WHAT IT DOES
1. Command: python src/main.py --ticker AMD. Pull prices with the free yfinance library.
2. 7 Claude calls, one per bot: Trend, Momentum, Value, News, Sentiment, Devil's Advocate, Risk. Each votes YES or NO as JSON with one reason.
3. 5 of 7 YES and no Risk veto = a ticket (entry, stop, target, size at 1% of a pretend $10,000). Otherwise no trade. Save to tickets/.

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 .env in .gitignore.

Starter vs finished

Starter (free, this prompt) Finished (AI Desk)
Works on your computer ✅ ✅
Runs your watchlist automatically ❌ ✅
Tested bot prompts ❌ ✅
Bot scorecard (who is right most) ❌ ✅
Phone tickets ❌ ✅
Tested by us, with setup support ❌ ✅

Troubleshooting

Problem Fix
It answers as one voice, not 7 Reply: "Answer as all 7 bots, one line each, then the vote."
Every idea passes Ask the Risk bot to be stricter: "No stop = no trade."
It makes up news Paste the news yourself with a date and link.

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.

Educational only. Not financial advice. It never places trades for you. You make every decision.