EvalKit Docs

    Simulations and scenarios

    Agents, scenario sets, simulation runs, scoring, compare, red team, quota, artifacts, cancel, and the SDK’s generate and evaluate routes.

    This page — Simulations and scenarios — is being written now and will replace this note in the next edit.

    PreviousReview queues, scores and RL datasetsNextAlerts, notifications and cost

    EvalKit is built by Syntropylabs. Published on PyPI and npm.