Claude Code 团队谈代码审查：从人工把关到持续检查
Quoting Addy Osmani, Morgan Westlee Lunt, and Qing Wang
Addy Osmani、Morgan Westlee Lunt 和 Qing Wang 在《How the Claude Code team does code review》中提出，用“有没有人读过代码”来判断风险并不准确，更该问的是这次改动可能出什么问题、该由哪种检查（自动或人工）来发现。
16th October 2026
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
来源：Simon Willison · simonwillison.net