Quoting Addy Osmani, Morgan Westlee Lunt, and Qing Wang
The Claude Code team uses continuous Claude review so humans focus on higher-level code risks.
Addy Osmani, Morgan Westlee Lunt, and Qing Wang describe how the Claude Code team treats code review as a continuous check rather than an end-of-process gate. Claude reviews and fixes most routine mistakes before a human is asked to look. Human attention is saved for higher-level questions about what could go wrong with a change.
- Review runs continuously, more like spellcheck than a final PR gate.
- Claude reviews and fixes most changes at least once before a human looks.
- Human attention is reserved for higher-level risk and scrutiny.
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?" Asking that question also changed when review happens. Before, review was a gate at the end of the road: write the code, open a PR, wait for your colleague. Now, review runs continuously, more like spellcheck while you write. Most changes have been reviewed and fixed by Claude at least once before a human is asked to look. This catches most routine mistakes, and saves team attention for higher-level questions and scrutiny. — Addy Osmani, Morgan Westlee Lunt, and Qing Wang , How the Claude Code team does code review Tags:…
This source does not provide full text. Read it at simonwillison.net.