- confirmed behavior from model-only hypotheses;
- successful execution from skipped or failed execution;
- analyzer absence from a clean analyzer result;
- a policy rejection from an infrastructure failure;
- current findings from baseline state.
Configure reviews
Evidence receipts
Trace what ran, what did not, and why
Every durable operation carries a correlation ID and produces structured
receipts for applicable stages. A receipt records inputs by immutable identity,
tool/model provenance, capability decisions, redacted command output, artifact
hashes, timing, and outcome.
Receipts distinguish:
Last modified on July 28, 2026
⌘I

