Agents That Get Smarter Every Trade
Learning cycles analyze performance, propose mutations, paper-test changes, and promote or roll back through a governed state machine.
Four Stages of Continuous Improvement
Each cycle runs automatically after a configurable number of trades. The agent reflects on what worked, what failed, and how to improve -- then proves it with data.
Analyze
Review recent trades, win rates, drawdowns, and signal accuracy across all positions
Propose
AI generates strategy mutations: adjusted thresholds, new data sources, improved sizing
Paper Test
Shadow-execute the mutation against live market data. Same prices, same timestamps -- simulated money
Evaluate and Gate
Must pass all harness safety rules and clear the configured benchmark. Otherwise, rolled back automatically
Mutation Pipeline State Machine
Every mutation moves through this pipeline. Auto-mode applies changes automatically when promoted. Manual mode requires your approval at the EVALUATING stage. A code diff viewer shows exactly what changed before you decide.
Before and After: Learning Cycle #14
An illustrative example showing how a political momentum agent can be evaluated over repeated learning cycles.
Intelligent Mutation Engine
The learning pipeline is not random trial-and-error. The AI analyzes which specific decisions led to losses, identifies patterns in losing trades, and generates targeted mutations designed to address those specific weaknesses.
Mutations can adjust thresholds, add new data source integrations, change position sizing algorithms, modify entry/exit timing, or refactor evaluation logic entirely. Each mutation is a minimal, focused change that can be independently validated.
- Root-cause analysis on every losing trade
- Targeted mutations, not random changes
- Full version history with instant rollback
- Optional human approval before any change deploys
# Target: Reduce false positives in
# low-volatility periods
class Mutation_14:
type = "threshold_adjustment"
target = "evaluate.threshold"
changes = {
"threshold": 3.0 -> 2.4,
"vol_filter": True,
"min_volume": 1000,
}
rationale = """
Analysis of 23 losing trades shows
68% occurred in low-volume markets.
Adding volume filter and lowering
threshold to capture more high-
confidence signals."""
backtest_result = {
"win_rate": 0.687,
"sharpe": 1.94,
"status": "APPROVED"
}
Learning With a Control Plane
Self-learning does not mean uncontrolled. Every mutation is paper-tested against live market data before deployment. Losing trades are classified as structural, noise, or sizing -- and structural failures become permanent safety rules.
The control plane includes a circuit breaker that halts trading after consecutive losses, a rate limiter, and harness cases that accumulate over time. Safety only grows. Every decision is recorded in an immutable evidence trail.
- Paper-tested mutations against live market data
- AI loss classification: structural, noise, or sizing
- Monotonic harness rules that only accumulate
- Circuit breaker and rate limiter on every signal
- Immutable evidence trail for every decision
You Control the Learning
Fine-tune every aspect of how your agents learn and evolve.
"learning_enabled": true,
"cycle_trigger": "every_50_trades",
"auto_approve": false,
"min_improvement": 0.05,
"max_mutations_per_cycle": 3,
"backtest_window_days": 90,
"rollback_on_drawdown": 0.15,
"notify_on_learn": true,
"version_retention": "all"
}
Let Your Agents Learn While You Sleep
Continuous improvement, zero maintenance. Start with a simple strategy and watch it evolve.