Quoting Addy Osmani, Morgan Westlee Lunt, and Qing Wang
Anthropic's Claude Code team replaced PR-gate code review with continuous AI-driven review during development
“We think "did a human read the code?" is an imprecise proxy for "what could go wrong with this change, and which check—automated or human—is the right one to catch it?"”
Anthropic's Claude Code team published how they restructured code review by shifting from a human-gate at PR time to continuous AI review while code is being written. Claude reviews and fixes most changes before a human ever sees them, reserving human attention for higher-level concerns. This is a notable signal of how AI-native engineering teams are rethinking foundational dev workflows.