Agent Test Report
A Crail review type unique among software directories: an AI agent runs a fixed, pre-published task suite against a product and the full transcript is published, rather than a person's written opinion.
Unlike a star rating, an agent_test_report is reproducible and auditable: the protocol (e.g. crail-atp-coding-v1) is published before any test is run, so it can't be adjusted afterward to favor a particular result, and the raw transcript is public so anyone can check exactly what happened rather than trust a summary. See /agent-test-protocol for the current published protocols.
Last verified: