Paper workflow
COMPLETESeven authorized multi-leg option round trips completed and the account finished flat at $100,125.91.
paper_evidence=true · live_claim=falseBounded AI · Defined risk · Auditable abstention
Evidence Governor separates market detection, option construction, AI criticism, and execution authority. The language model can review evidence. It cannot invent a contract, change size, or reach an order tool.
Authority map
The agent is autonomous only inside a deterministic safety envelope. Each component has one job, and the AI has less authority than the risk governor.
30 real model calls
Choose a historical case to see exactly what the AI selected, which evidence IDs it cited, why four answers were rejected, and what the outcome revealed only afterward.
Outcome audit
The AI improved the paired result by abstaining or switching in four economically different cases. But every available candidate in the accepted sample was non-positive, and the AI still lost money.
Bounded execution
The competition workflow executed, but the system keeps simulated fills, data quality, statistical promotion, and order authority as separate claims.
Seven authorized multi-leg option round trips completed and the account finished flat at $100,125.91.
paper_evidence=true · live_claim=falsePer-trade risk targeted 0.10% of current equity; daily loss was capped at 0.25% and $250; one spread at a time.
ai_sizing_authority=falseThe free options feed was Indicative, not OPRA. Simulated Paper fills do not prove live executability.
strategy_efficacy_claim=falseThe runtime could submit only code-locked Paper candidates and exact owned-leg closes. This public demo has no account or order access.
final_positions=0 · open_orders=0