#agent harness

With Thomas Pierrain and Vanessa Gossent, I revisit AI costs, hiring, parallel agents and the work we have to redo after delivery.

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.

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.

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

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