post trade mistake intelligence engine

The problem

Manual trade reviews are often superficial, ignoring the hidden costs of emotional decisions and execution errors. Traders struggle to see the statistical difference between a valid loss and a costly mistake, leading to repeated failures without a clear path to correction.

What it does

• Normalizes raw trade logs and journal entries into a structured analytical framework.
• Categorizes failures across entry, exit, risk, stop-management, and emotional dimensions.
• Quantifies the R-multiple impact of mistakes like stop deletion, chasing, and FOMO.
• Identifies correlations between execution errors and external contexts like time of day or market volatility.
• Generates a prioritized improvement plan with specific, testable trading rules and measurable goals.

Why this beats prompting it yourself

Generic prompts often hallucinate PnL calculations or fail to distinguish between a plan-based loss and a psychological mistake. This skill applies a rigid taxonomy and counterfactual analysis to ensure every dollar lost to poor discipline is accurately accounted for and corrected via rule-based remedies.

Use cases

• Reviewing a weekly trading session to identify which psychological leaks cost the most capital.
• Auditing a series of losses to determine if the strategy is failing or if the execution is flawed.
• Refining risk management by analyzing the frequency and impact of "revenge" position sizing.
• Creating a data-driven pre-trade checklist based on your most recurring execution errors.

Known limitations

Requires entry price, exit price, and initial stop loss to calculate accurate R-multiple impact. Cannot quantify impact if counterfactual data (like original stop levels) is missing from logs.