I built a QA agent that audits itself nightly. It has filed 79 findings against its own releases

说明与用途

Verdict 是一个 QA 代理，每晚自检自己的发布，已对自身 harness 提交 79 条发现并发布详细运行历史。

问题

Existing AI QA agents re‑audit a repo from scratch each run, never remembering past failures and never preventing code changes that introduce regressions.

结果

Verdict now autonomously audits itself nightly, filing 79 findings against its own harness, improving its failure taxonomy, and publishing detailed run histories and evaluation metrics.

工作流

• 1. Run verdict on a repo; 2. State file records baseline and delta; 3. Classify each red test (defect, stale, brittle, environment, flaky); 4. Record run outcome (pass, pass with risks, blocked, fail) and list untested areas; 5. Store signed run history; 6. Next nightly run audits previous release; 7. If a finding is resolved, name the axis not varied and test one point; 8. Publish eval scores, run history, findings, and accepted risks.

证据

It has filed 79 findings against its own harness so far

来源

Every release is audited by the previous one, nightly

来源