Behavior Evaluation Promise
Promise ID: promise.evaluation.
Behavior Evaluation gives users a bounded way to evaluate intentful behavior across supported dev and app surfaces when deterministic tests alone do not explain the behavior.
Links
- User workflow: Behavior Evaluation
- Maintainer evidence routes: Evaluation Surfaces And Runners, Reporting And Review Variants, Live Invocation Runtime
- Related cross-cutting rules: Reviewable Artifacts, Packet Freshness, Cost And Proof Freshness, Host-Owned Execution
Evidence State
Evidence status: open gap. Selected evidence bundles are shown in the user view without rerunning expensive eval loops, and maintainer routes own fixture and runner proof.
Verify evaluation links point to existing docs.
test -f docs/specs/user/evaluation.spec.md
test -f docs/specs/contracts/evaluation-surfaces-runners.spec.md