AI Council — Agent 4 of 8
Risk Assassin
Capital preservation
Drawdown charts show history. The Risk Assassin shows which trades and sizing decisions caused it — and whether your current risk profile can survive another streak.
Hunts capital destruction patterns, not trade count. Reads pre-computed risk metrics: max drawdown and recovery, oversized-trade breakdown with % of drawdown attribution, worst-case tail events, R-multiple stability, session risk profile, drawdown contributors, Kelly/ruin probability (Monte Carlo when available), and Sharpe/Sortino/Calmar.
What the Risk Assassin actually outputs
Not a chat summary — a structured forensic report from your canonical trade tape, with grades, benchmarks, and prioritized recommendations.
Sample Risk Assassin report
Illustrative output from a populated audit — same structure as the in-app agent renderer.
Risk Assassin's Assessment
Risk profile is cautionary: max drawdown 18.4% with accelerating recent leg. Four oversized trades account for 68% of drawdown dollar loss. R-multiple instability flagged — second-half avg R −0.4 vs first half.
Benchmark analysis
What you're doing well
Risk-adjusted returns remain positive despite drawdown pressure.
Core sizing tracks portfolio target on majority of trades.
Areas needing attention
4 trades at 1.4% avg risk vs 1.0% target drove majority of max drawdown loss.
R stddev 1.24 with −0.4R second-half drift — payoff distribution widening.
Recommended actions
Hard cap at 1.0× portfolio risk — no exceptions until 2 weeks without oversized trade.
Expected impact: Removes primary drawdown accelerator; historical oversized trades were net −$2,840.
Reduce size 25% after any 3-trade loss streak until equity recovers prior peak.
Expected impact: Cuts tail risk during loss clusters; aligns with half-Kelly recommendation.
What it reads from your tape
The Risk Assassin receives pre-aggregated metrics from your completed trades — not a generic chat summary. Every input comes from your canonical trade tape.
- →Maximum drawdown depth, recovery days, and drawdown acceleration
- →Oversized trades (>1.2× target risk) with % of max drawdown attribution
- →Worst single loss, worst daily loss, and max loss streak dollar impact
- →R-multiple stability (stddev, first vs second half delta)
- →Session risk profile and drawdown contributors in worst period
What it detects
- Oversized risk trades driving disproportionate drawdown
- Drawdown acceleration and unstable R-multiple drift
- Ruin-adjacent sizing vs Kelly optimal and half-Kelly
- Session-level over-risk clustering
What it delivers
- Risk grade and sustainability assessment
- Drawdown, sizing, ruin, and worst-case analysis blocks
- Danger zones and vulnerabilities with dollar impact
- Survival plan with prioritized risk recommendations
Know if your risk profile survives the next streak — before it arrives
Run the Risk Assassin on your completed trades. Inspect the full AI Council free on a populated demo account — read-only, no credit card.
Example finding
“4 oversized trades (avg 1.4% risk vs 1.0% target) contributed 68% of max drawdown; ruin prob 3.2% with R instability flagged.”
How it fits the Council
The Risk Assassin 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 5Setup Surgeon
Setup edge & decay
Learn more Agent 6Regime Cartographer
Market environment fit
Learn more Agent 7Entry & Exit Judge
Opportunity capture forensics
Learn more Agent 8Chief Coaching Officer
Synthesis & prioritization
Learn moreFrequently asked questions
Frequently asked questions
What is ruin probability in this context?
Ruin probability estimates the likelihood of hitting a defined capital threshold given win rate, payoff ratio, and sizing variance. When you have run Monte Carlo in the app, the agent uses that real simulation; otherwise it uses a conservative estimate.
How is this different from a max drawdown chart?
Drawdown charts show history. The Risk Assassin attributes drawdown to specific oversized trades (drawdown_contributors), sessions (session_risk_profile), and tail events (worst_case_summary) — so you know what to fix, not just that DD happened.
What triggers an oversized trade flag?
Any completed trade where effective risk % exceeds 1.2× your portfolio default_risk_percentage. oversized_trades_breakdown shows count, total P&L, and pct_of_max_drawdown.
How is this different from the Behavioral Psychologist?
The Behavioral Psychologist grades emotional leakage (revenge, FOMO, compliance). The Risk Assassin grades capital survival: drawdown depth, ruin probability, Kelly alignment, and sizing-driven drawdown attribution.
What data improves the analysis?
account_risk_percent on every trade unlocks sizing forensics. realized_r_multiple enables R-stability analysis. Running Monte Carlo in-app replaces ruin estimates with simulation-backed probabilities.
See Risk Assassin on your trade history
Inspect the full AI Council on a populated account — every agent visible, read-only, no credit card.