ProEA Lab · Topic hub
AI & trading: claims, audited
AI arrived in retail trading as a sales word before it arrived as a capability. The gap between those two is where accounts get hurt — perfect-looking optimized backtests, prediction claims nobody can verify, bots sold on renders instead of code.
This cluster applies one standard to every AI claim, including our own products' AI features: show the mechanism, show the failure mode, never promise outcomes. The overfitting audit is the piece to read before trusting any AI-built system.
Start here
AI Backtest Overfitting: How to Audit a Perfect Result Before You Trust It
14 min read
AI backtest overfitting audit →
the checks, in order
Evolution Lab →
stress-testing for AI-built systems
The Watch →
22 desks, 18 AI and 4 rule-driven
Start here
How to Use AI for Trading: What ChatGPT and Claude Can and Can't Do
Use ChatGPT or Claude as a reviewer, a rule-keeper and a research assistant, not as a forecaster. Six jobs, what AI can and can't do in each, the evidence behind the limits, and three prompts to copy.
AI Backtest Overfitting: How to Audit a Perfect Result Before You Trust It
Describe a strategy to AI, or let an EA/indicator generator optimize it, and you'll get a gorgeous equity curve in minutes. You didn't find an edge — you ran a search. And a big enough search always finds a winner, even when there's nothing there.
How to Build a Trading Bot With AI (ChatGPT or Claude)
ChatGPT or Claude can write a working trading bot in an afternoon, but working code is not an edge. Here is the build workflow, the five things AI leaves out, an audit for the failures that stay silent, and the four decisions you keep.
Build and verify
What Is Look-Ahead Bias? How to Find It in a Backtest
Look-ahead bias is a backtest using information that didn't exist yet when each trade was decided. The five places it hides, how to trace each one, and why a one-bar delay test can point at a leak but can't prove one.
AI Found a Winner.
Test ten thousand strategies and one will look brilliant by pure luck. AI tests ten thousand before lunch. Here is the test quant funds run — and retail skips — that tells a real edge from a coincidence.
Do Forex EAs Actually Work? Grid Risk, AI Bots and a Pre-Buy Test
An EA automates a set of rules; it doesn't supply an edge, and no representative dataset says what share of EAs work. Here is why EAs fail, why grid and martingale robots look safest just before they aren't, five checks for an AI trading bot, and a four-step test to run before you pay.
Agents and account access
AI Trading Agents: What They Can Do With Broker Access, and the Risks
Robinhood, Alpaca and ThinkMarkets now let an AI assistant place orders in a real brokerage account. Here is what an agent can do with that access, what the brokers and eight members of Congress say about the risks, and how to set one up so that a mistake stays small.
TradingView MCP Server: Official vs Community
TradingView's official MCP server gives Claude delayed market data, the screener, watchlists and price alerts on Essential plans and up. A community server drives TradingView Desktop and can compile Pine. How to connect each one, and where each can hurt you.