Addy Osmani· @addyosmani · X·· 16 天前AI 评分59
AI 导读
Addy Osmani 分享用 Agent 获取好结果的关键是验证，认为审查若不预先明确“完成”的定义，每次都可能找到新的可改进点。他建议给 Claude 可运行的检查，如 bash 命令、测试或在浏览器中点击应用，让它通过后再宣布完成，确保没有阻塞事项时即可合并发布。
正文 · 原文
Verification is one of the most important things for getting great results out of your agent.
Clearly define "done" before code review starts.
A reviewer, human or agent, asked to find bugs without this may still find something that could be improved.
Give Claude checks it can run (bash commands, tests, clicking through the app in a browser) and have it pass that too before it says it's finished.
When nothing blocks merge and ship.
Asking Claude to review your code is a slot machine. Every review finds brand new bugs. Review again: more. Review a tenth time: it still finds something. It never runs out of bugs to find... so how do you decide your code is actually done?在 X 查看被引用的帖子
来源：Addy Osmani · x.com