How the Claude Code team does code review
Why CEREBRO kept it
Claude Code team code-review process; direct agent deep-dive
The text below is an automated extraction of the article at https://claude.dev/blog/solving-code-review-at-anthropic/, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (claude.dev).
How do you review code at the volume agents produce it? On the Claude Code team, once we had high coverage and deep reviews, we started optimizing for the minimum amount of human review time that doesn't raise reverts or incidents. We've said before that Claude writes about 90 percent of Claude Code's own code. So how do we review code at the volume we produce it? Does anyone read code anymore? And if something breaks, who catches it? This post covers the code review flow on the Claude Code team and how it has evolved. From June to September, merged pull requests to Claude Code's codebase more
Community take
Skeptics call the 30k-merged-changes-per-day figure implausible and warn that letting engineers close security false positives without AppSec sign-off could lower revert rates while adding vulnerabilities.
Backlinks
Appeared in 1 briefing
Related
Shares tags: ai/agents · cerebro/signal
Also from claude.dev
Only signal from claude.dev so far.