智能体
x.com ·
@Addy Osmani (@addyosmani)
Addy Osmani:为 AI Agent 编码定义可执行的“完成”标准
Addy Osmani 在 X 上分享 agent 编码的验证经验:在代码审查开始前明确定义“完成”标准,并给 Claude 提供可运行的检查(bash 命令、测试、浏览器点击流程),要求其通过这些检查后才声明任务完成。他引用另一用户的观察称,让 Claude 反复审查代码会不断发现新问题,因此需要明确的完成条件来终止循环。该内容为经验性建议,未提供实验数据或可验证证据。
AI推荐理由 Addy Osmani 提出 agent 编码工作流中的验证实践:在代码审查前明确定义“完成”标准,并给 Claude 可执行的检查(bash 命令、测试、浏览器点击流程),通过后才算完成。这是来自知名开发者的经验性建议,属于可操作的方法论,但无实验数据或可验证证据支撑,且引用推文中的“老虎机”比喻只是个人观察,不能当作已证实的结论。
62
浏览 33,759
点赞 469
评论 77
转发 44
正文
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.