Claude Code Team Details Its AI-Assisted Code Review Workflow
The Claude Code team has described a workflow that delegates most routine code reading to automated systems while using risk tiers to determine when human approval is required for sensitive changes. The team says that from June to September, merged pull requests more than doubled while the share requiring reverts fell by more than 40%. It also says revised review rules raised the first-pass resolution rate from 65% to 78% and reduced average review rounds from 2.08 to 1.32. These figures are first-party claims and have not been independently verified.
The reports describe a concrete model for reviewing agent-generated code at scale: automated checks handle routine review, risk tiers determine when people must approve changes, and staged releases and rollback provide safeguards. The team says this shifted most code reading to machines without removing human review, though the reported results remain first-party claims.
How the Claude Code team does code review / claude.dev Blog
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.
AUTHOR
Addy Osmani, Morgan Westlee Lunt, and Qing Wang