AI Council — Agent 6 of 8
Regime Cartographer
Market environment fit
The same setup can win in trend and bleed in chop. The Regime Cartographer maps which market environments carry your edge — and which ones are costing you money.
Reads pre-computed regime metrics: volatility distribution and performance_by_regime (high/normal/low vol), quant_regime_performance from Quant Lab, session and day-of-week splits, directional alignment (long vs short by vol), per-setup volatility sensitivity, ATR percentiles, and pre-built opportunity/danger lists — then coaches regime-aware trade selection.
What the Regime Cartographer actually outputs
Not a chat summary — a structured forensic report from your canonical trade tape, with grades, benchmarks, and prioritized recommendations.
Sample Regime Cartographer report
Illustrative output from a populated audit — same structure as the in-app agent renderer.
Regime Cartographer's Assessment
Edge is regime-dependent: normal volatility carries 2.35 PF and +$4,250 P&L, while high vol bleeds −$320. New York session shows size drift — 62% win rate but −0.1R expectancy. Long-biased with chop-regime underperformance.
Benchmark analysis
What you're doing well
50 trades, 62% win rate, +$4,250 — your primary edge environment.
London session shows positive avg R across 28 trades.
Areas needing attention
23 trades in high volatility with negative total P&L — reduce size or sit out.
62% win rate masks negative expectancy — classic size-drift pattern in US hours.
Recommended actions
Cut high-vol exposure by 50% or require A+ setup only when volatility_regime = high.
Expected impact: Avoids ~$320/mo in high-vol losses per pre-computed danger block.
Audit New York session sizing — win rate is fine but avg R is negative.
Expected impact: Fixes size drift without abandoning the session entirely.
What it reads from your tape
The Regime Cartographer receives pre-aggregated metrics from your completed trades — not a generic chat summary. Every input comes from your canonical trade tape.
- →Volatility regime distribution and performance (high / normal / low vol)
- →Quant Lab GMM regime performance (trend, chop, etc.) when quant_regime is stamped
- →Session-level win rate, expectancy, and avg R (Asia, London, New York)
- →Day-of-week performance and directional long/short alignment by regime
- →Per-setup volatility sensitivity — setups that only work in specific vol conditions
What it detects
- Negative expectancy in specific volatility or quant regimes
- Session-level bleed — high win rate but negative R (size drift pattern)
- Directional misalignment — long-biased edge in bear vol or vice versa
- Regime-sensitive setups with large expectancy spread across vol buckets
- Over-concentration in a single volatility regime (>70% of trades)
What it delivers
- Regime assessment with awareness grade and best/worst regime labels
- Volatility regime performance table and session performance table
- Pre-computed regime opportunities and dangers with monthly savings
- Regime rules, directional bias, and prioritized regime_recommendations
Stop trading your edge in the wrong market environment
Run the Regime Cartographer on your completed trades. Inspect the full AI Council free on a populated demo account — read-only, no credit card.
Example finding
“Tuesday NY open: 62% win rate but −0.1R expectancy — size drift; high_vol regime PF 0.82 vs normal_vol 2.35.”
How it fits the Council
The Regime Cartographer runs in parallel with six other specialists on the same audit period. Each agent sees metrics tuned to its domain. When specialists disagree, they debate transparently in The Situation Room before the Chief Coaching Officer synthesizes everything into a dollar-ranked Kill List.
- 1Seven specialists analyze pre-computed metrics in parallel
- 2Disagreements surface in The Situation Room debate transcript
- 3Chief Coaching Officer ranks preventable leakage into your Kill List ($/month)
Meet the other agents
Performance Analyst
Profitability & statistical edge
Learn more Agent 2Behavioral Psychologist
Discipline & emotional leakage
Learn more Agent 3Execution Tactician
Timing & fill quality
Learn more Agent 4Risk Assassin
Capital preservation
Learn more Agent 5Setup Surgeon
Setup edge & decay
Learn more Agent 7Entry & Exit Judge
Opportunity capture forensics
Learn more Agent 8Chief Coaching Officer
Synthesis & prioritization
Learn moreFrequently asked questions
Frequently asked questions
How does it determine market regime?
Volatility regime uses ATR-based high/normal/low classification stamped on each trade. Quant regime uses Quant Lab GMM tags (quant_regime, quant_regime_label) when the pipeline has run. Legacy bull/bear/sideways uses market_regime when populated. The agent cites data_coverage to show how much of your tape is classified.
Can it tell me when NOT to trade a setup?
Yes. per_setup_volatility_sensitivity flags setups where expectancy diverges across vol buckets. Combined with quant_regime_performance and session_performance, the agent quantifies dollar cost of trading outside your edge environment and surfaces kill-list candidates in regime_dangers.
How is this different from the Setup Surgeon?
The Setup Surgeon ranks and kills setups — drift, compliance, and per-setup quant_regime_dependency. The Regime Cartographer maps portfolio-level environment fit: vol distribution, session/day splits, directional alignment, and cross-setup regime opportunities/dangers. They complement each other; the CCO synthesizes both.
What if quant_regime is not on my trades?
The agent still analyzes volatility_regime, session_performance, day_of_week_performance, and directional_alignment. data_coverage.quant_regime_coverage_pct tells you how much of the tape lacks Quant Lab tags — conclusions are weighted accordingly.
How many trades do I need per regime bucket?
Volatility splits appear from the first classified trade. Pre-computed opportunities and dangers require 5+ trades per regime bucket. Per-setup volatility sensitivity needs 5+ trades per setup and 3+ per vol sub-bucket. Session analysis needs entry timestamps.
See Regime Cartographer on your trade history
Inspect the full AI Council on a populated account — every agent visible, read-only, no credit card.