<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>团队管理 on Plbear | 后端架构 · AI工程 · 云原生技术博客</title><link>https://www.plbear.com/tags/%E5%9B%A2%E9%98%9F%E7%AE%A1%E7%90%86/</link><description>Recent content in 团队管理 on Plbear | 后端架构 · AI工程 · 云原生技术博客</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Thu, 12 Nov 2026 14:00:00 +0800</lastBuildDate><atom:link href="https://www.plbear.com/tags/%E5%9B%A2%E9%98%9F%E7%AE%A1%E7%90%86/index.xml" rel="self" type="application/rss+xml"/><item><title>把三个 AI Agent 当同事管：一套可复算的目标记分卡</title><link>https://www.plbear.com/posts/2026-11-12-three-agents-scorecard-playbook/</link><pubDate>Thu, 12 Nov 2026 14:00:00 +0800</pubDate><guid>https://www.plbear.com/posts/2026-11-12-three-agents-scorecard-playbook/</guid><description>我给三个常驻 AI Agent 建的第一版目标记分卡，11 条判据 6 处不干净：卡面数字不是命令算的、命令指着已废弃的文件、口径一天换三回。这篇讲可复算判据、环形交叉复算、动作响应与休眠判据，附 8 条纪律。</description></item></channel></rss>