How the Claude Code team does code review

The Claude Code team leverages a structured code review process despite Claude writing 90 percent of its own code. During the research preview, substantive review comments on internal PRs increased from 16% to 54%. Large PRs (over 1,000 lines) often receive findings, while smaller ones are typically clean. Repositories are configured for Quick, Standard, or Deep review, with Deep review reserved for critical areas where a missed bug is costly. Although automated, detecting bad merges still relies on authors, on-call personnel, and monitoring dashboards.

This report details how the Claude Code team reviews code, moving from 16% to 54% substantive review comments during its research preview, unlike other teams that might reduce human oversight with AI code generation.