Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for traders

Trade Idea Red-Team Agent

Each trade idea tested against counter-evidence before entry

Trade Idea Red-Team Agent: what goes in, what the agent does and what you get

What it does

Traders fall in love with their ideas and stop looking for reasons they could be wrong. When the trader writes a trade idea, this agent argues the other side. It lists the idea's key assumptions and searches news, data and charts for evidence against each one. It checks positioning data, upcoming events and similar past setups. For each assumption it rates the counter-evidence as weak, moderate or strong, citing sources. If an assumption cannot be tested with available data, it says so. It flags assumptions the market already prices in. It then asks the trader to state what would prove the idea wrong and checks that the stop matches that point. If not, it asks for an adjustment and checks again. The trader decides whether to trade. Edge case: the idea depends on a rate cut already priced into futures.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedNo 1 STARTS WHEN Idea submitted 2 DOES List key assumptions 3 USES A TOOL Search for counter-evidence 4 DOES Rate counter-evidence per assumption 5 CHECKS THE RESULT Does the stop match the invalidation point? If not: ask the trader to restate invalidation or adjustthe stop. Back to step 2. 6 YOU APPROVE Trader decides to trade or pass 7 RESULT Red-team note saved with the idea
Read the steps as a list
  1. Idea submitted
  2. List key assumptions
  3. Search for counter-evidence
  4. Rate counter-evidence per assumption
  5. Does the stop match the invalidation point?If not: ask the trader to restate invalidation or adjust the stop. Back to step 2.
  6. Trader decides to trade or passThe agent waits here for your OK.
  7. Red-team note saved with the idea

How it decides

It rates counter-evidence per assumption and checks the stop sits at the invalidation point.

  • Strong counter-evidence on a main assumption: suggest smaller size or pass
  • Assumption already priced in: flag
  • Stop far from invalidation: ask to adjust

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Sources to search
  • Number of assumptions
  • Rating scale
  • Note format

What keeps you in control

It always asks you first

  • Trading the idea

Hard limits

  • Never trades
  • Never tells the trader what to do

It stops when

  • Done: note saved
  • Stop: idea has no testable assumptions

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensA trader proposed a long position in regional banks, assuming rate cuts would lift lending. The agent found futures already priced three cuts and rated that strong counter-evidence. The stop check failed: the stop was 8% away, but the stated invalidation was a break of a level 4% away. The trader moved the stop to 4.5%, the recheck passed, and the trader took half size.

More agents for traders