Claude writes about 90% of Claude Code's code
Anthropic's engineering team explains how they manage code review for Claude Code, which is largely written by AI agents. They have shifted from manual line-by-line reviews to automated, continuous review processes to handle high volumes of changes.
Why it matters
This represents a significant shift in software engineering workflows, demonstrating how AI can scale development while maintaining code quality.
[ H ] HOME [ M ] MODS [ D ] DOCS [ T ] TERMINAL Engineering How the Claude Code team does code review 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 than doubled while the share that had to be reverted fell by more than 40 percent.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in