#code review

A test that passes for the wrong reason leads to a practical way to assess how a team scopes, verifies, explains, fixes and hands over an agent’s work.

My conversation with Bruno Soulez on context engineering, agent harnesses and code review: what I delegate and what I still check.

Three months, 1,011 pull requests and 8,728 inline AI review comments: 4.5% got a visible human response. What the data shows, and what it cannot.

AI can shorten implementation while specification, review, CI, and rework absorb the saved time. Instrument the full flow before adding more generation.

Opus 5.5 is the next reviewer baseline to test: set effort explicitly, update the API adapter, and keep a second reviewer only when it catches verified defects.

When the same accepted correction returns, test whether it belongs in a linter, type, test, example, repository rule, checklist, or architecture decision.

Compare independent review with self-review and deterministic checks. Measure rescued defects, false acceptances, regressions and the cost of another pass.

A review signal matters only when its provider, commit SHA, coverage, execution state, publication, and place in branch policy are explicit.

Build a bounded review loop with frozen inputs, separate execution and outcome fields, retry limits, evidence handoffs and human escalation.

Review, business context, costs and product development: my synthesis of Dev With AI on October 12, 2026, with the full illustrated conference report.

Run local, CLI, and remote reviewers with explicit trust boundaries, least privilege, structured findings, budgets, degraded states, and shutdown controls.

Dev With AI talk guide: agent harnesses, local checks, AI reviews, bounded corrections and results tied to the right commit. Examples and slides.