Simulation & research platform · Not financial advice
Simulation only. Nothing here uses real money or connects to a real brokerage account. This is a research tool.

AI judges

Four AI specialists that review the agents from different angles. They vote before big decisions. You control what each judge cares about, and how loud its vote is.

Run the panel

Pick an experiment. Each enabled judge writes a short verdict. Their weighted vote becomes the overall panel decision.

Risk judge
Enabled

Looks for hidden danger. Rejects strategies that rely on luck, thin data, or unrealistic assumptions.

Vote weight25%

Model: GPT-4o-mini. Prompt changes take effect on the next review round.

Sceptic judge
Enabled

Challenges good results. Assumes agents might have gotten lucky — and looks for proof they didn't.

Vote weight25%

Model: GPT-4o-mini. Prompt changes take effect on the next review round.

Evolution judge
Enabled

Watches the health of the whole learning process. Suggests more variety when things get stale.

Vote weight25%

Model: GPT-4o-mini. Prompt changes take effect on the next review round.

Scientist judge
Enabled

Forms hypotheses about what makes strategies work. Suggests new experiments.

Vote weight25%

Model: GPT-4o-mini. Prompt changes take effect on the next review round.