Spec-first agentic delivery on a live internal repo
AI-SDLC- proposed
- voting
- running · 45d
- measuring
- concluded
Preregistration · v1 · 6 Jul 2026 · immutable after start
Hypothesis
On the firm's internal engagement-tracker repo, features delivered spec-first (human-reviewed spec, agent-written code, human at merge) ship with at least 40% lower review time per PR and no more post-merge defects than the pod's trailing-quarter baseline.
Kill condition
Kill if review time per PR is not at least 15% lower after 12 features, or if post-merge defects per feature exceed 1.5× baseline at any point.
Running notes · fed from harness sessions and by the pair
- manual2 Sep 2026SK Sam Kowalczyk
Three features to go. Asking for two more weeks rather than concluding at 17; the last three are the largest and will test the drift question.
- harness28 Aug 2026SK Sam Kowalczyk
17 features; review time -41%; 1 defect at 14d (baseline rate would predict 2.3); rewrites 1.4
- manual14 Aug 2026TO Tom Okafor
Overrunning. Features 9–14 stalled: the pod's product owner was on leave and nobody else would sign a spec. Spec-first needs a spec signer; that is a finding in itself.
- harness31 Jul 2026SK Sam Kowalczyk
8 features shipped; review time -47% vs baseline; defects 0; spec rewrites avg 1.6
- manual6 Jul 2026SK Sam Kowalczyk
Predicted 35% lower review time, confidence 0.55. The unknown is how many spec rewrites it takes before the agent stops drifting.
Harness notes are auto-captured from Claude Code sessions: model, date, commit, session reference. Never the transcript, code or paths.