How We Run Lullwood With Eleven Claude Agents and One Release Train

Описание и применение

В Lullwood 11 AI‑агентов работают над одной репозиторием. Ограничив блокирующие обзоры только критическим изменениям, команда сократила время проверки и удвоила скорость выпуска.

Задача

Reviewing every change in a multi‑agent development environment consumed more effort than creating new features, limiting release velocity.

Результат

By limiting blocking reviews to high‑risk changes, the team reduced review overhead, doubled shipping throughput, and maintained acceptable defect rates.

Рабочий процесс

• 1. Agents submit pull requests to the shared repo.
• 2. Automated checks run on all PRs.
• 3. High‑risk PRs are routed to a Code Reviewer for blocking review.
• 4. Low‑risk PRs merge automatically after checks pass.
• 5. Release train incorporates merged changes and deploys to Vercel.

Доказательства

In one week the two agents building the game ran 803 sessions between them, and the two agents gating that work ran 853.

Источник

Docs, tests and copy ship the moment checks are green, with no review.

Источник

The engine's core simulation, persistence, anything touching secrets or merge rules, and release cuts still need a blocking review before they land.

Источник