Agentic QA on a regression-heavy codebase
Fully Agentic QA- proposed
- voting
- running
- measuring · 3d
- concluded
Preregistration · v1 · 11 May 2026 · immutable after start
Hypothesis
An agent maintaining the regression suite on an internal 60k-line service lifts mutation score from 0.52 to at least 0.75 within three weeks, with no rise in escaped defects during the run.
Kill condition
Kill if mutation score is under 0.6 by day 10, or if any agent-written test is found to assert on its own mocked output rather than behaviour (two instances kills).
Running notes · fed from harness sessions and by the pair
- harness31 Aug 2026SK Sam Kowalczyk
week 3: mutation 0.77; escaped defects 0; into measuring
- manual24 Aug 2026LF Lena Fischer
Reviewed 40 tests. One hollow assertion found (asserted a mock returned its own fixture). One instance, not two. Flagged the pattern; agent rule updated.
- harness14 Aug 2026SK Sam Kowalczyk
week 1: mutation 0.52 -> 0.61; 214 tests added; 0 escaped defects
- manual11 May 2026SK Sam Kowalczyk
The fallback that survived the vote after g-agentic-qa-full was rejected. Predicted 0.7, confidence 0.5.
Harness notes are auto-captured from Claude Code sessions: model, date, commit, session reference. Never the transcript, code or paths.