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

Strategy Drift and Drawdown Monitor Agent

A clear status of whether the live strategy is inside its tested range, with a size or pause proposal when it is not

MonitoringRisk managementDecisionsFinance
See how it worksGet access
Strategy Drift and Drawdown Monitor Agent: what goes in, what the agent does and what you get

What it does

Strategies decay quietly, and the trader sees it only after a painful run. After each close, this agent updates the strategy's live statistics: win rate, average loss, profit factor and drawdown. It compares them to the range the trader wrote down from the backtest. When a statistic leaves the range, it checks whether the cause is the market, such as a volatility regime change, or the trader breaking their own rules. It tags rule-break trades and recomputes the statistics without them. If the strategy is still outside its range, it proposes reduced size or a pause, with the numbers behind the proposal. The trader approves any change. Edge case: a drawdown driven by two trades taken against the rules is reported as a discipline problem, not a strategy problem.

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, continueYes, continueApprovedNoNo 1 STARTS WHEN Market closes 2 USES A TOOL Load the day's fills and the trade journal 3 DOES Update win rate, average loss, profit factor anddrawdown 4 DOES Compare each stat with the backtest range 5 CHECKS THE RESULT Are all stats inside the range? If not: tag trades that broke the rules and recomputethe stats without them. Back to step 3. 6 USES A TOOL Check volatility and market regime against thebacktest period 7 CHECKS THE RESULT Is the strategy still outside its range afterexclusions? If not: report as a discipline issue and list therule-break trades. Back to step 3. 8 DOES Draft a proposal: reduce size by a set step or pause 9 YOU APPROVE Trader approves the size change or pause 10 RESULT Daily strategy health note
Read the steps as a list
  1. Market closes
  2. Load the day's fills and the trade journal
  3. Update win rate, average loss, profit factor and drawdown
  4. Compare each stat with the backtest range
  5. Are all stats inside the range?If not: tag trades that broke the rules and recompute the stats without them. Back to step 3.
  6. Check volatility and market regime against the backtest period
  7. Is the strategy still outside its range after exclusions?If not: report as a discipline issue and list the rule-break trades. Back to step 3.
  8. Draft a proposal: reduce size by a set step or pause
  9. Trader approves the size change or pauseThe agent waits here for your OK.
  10. Daily strategy health note

How it decides

A stat is out of range when it falls outside the backtest band. The agent recomputes without rule-break trades before proposing action, and proposes a pause only if the strategy is still out after that.

  • Flag a drawdown that exceeds the backtest maximum by 25%
  • Treat win rate below the band for 30 trades as drift
  • Exclude trades tagged as rule breaks before judging the strategy
  • Propose size cut in steps of 25% before a full pause

Make it yours

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

  • Backtest ranges for each stat
  • Minimum trades before judging (default 30)
  • Size cut step (default 25%)
  • How rule breaks are tagged in the journal

What keeps you in control

It always asks you first

  • Reducing size or pausing the strategy

Hard limits

  • Never changes position size or places orders itself
  • Does not move the backtest range on its own

It stops when

  • Done: health note issued and any proposal approved or declined
  • Stop: fewer than 20 live trades exist

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 happensAfter 42 live trades, the agent saw win rate at 38% against a backtest band of 45 to 58%, and drawdown at 11% versus a 9% maximum. Two trades had skipped the stop rule. Removing them lifted win rate to 41%, still below band, so the check failed to clear. It proposed cutting size 25% and noted high volatility since March. The trader approved the cut.

More agents for traders

Analysis · Automation

Watchlist Setup Screening Agent

A ranked short list of watchlist candidates that meet the trader's rules and pass the safety checks

10 steps2 checks1 job
Planning · Creating

Weekly Trading Plan Builder Agent

An approved weekly plan with scenarios, levels, events and total planned risk inside the trader's limits

10 steps2 checks2 jobs
Quality control · Analysis

Backtest Sanity Check Agent

A report showing how much of the backtest edge survives realistic costs and out-of-sample testing

10 steps2 checks1 job
Analysis · Decisions

Execution Quality and Slippage Audit Agent

A monthly report of execution costs by broker, order type and time, with approved changes that cut them

11 steps2 checks2 jobs