<?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>上下文工程 on BestAgent</title>
    <link>https://bestagent.fun/tags/%E4%B8%8A%E4%B8%8B%E6%96%87%E5%B7%A5%E7%A8%8B/</link>
    <description>Recent content in 上下文工程 on BestAgent</description>
    <image>
      <title>BestAgent</title>
      <url>https://bestagent.fun/favicons/web-app-manifest-512x512.png</url>
      <link>https://bestagent.fun/favicons/web-app-manifest-512x512.png</link>
    </image>
    <generator>Hugo</generator>
    <language>zh-CN</language>
    <lastBuildDate>Tue, 28 Jul 2026 00:00:00 +0800</lastBuildDate>
    <atom:link href="https://bestagent.fun/tags/%E4%B8%8A%E4%B8%8B%E6%96%87%E5%B7%A5%E7%A8%8B/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>为什么很多 AI Agent 教程看懂了还是不会做</title>
      <link>https://bestagent.fun/posts/ai-agent-book-hidden-knowledge/</link>
      <pubDate>Tue, 21 Jul 2026 00:00:00 +0800</pubDate>
      <guid>https://bestagent.fun/posts/ai-agent-book-hidden-knowledge/</guid>
      <description>会调用模型、接上工具、跑通 ReAct 只是起点。本文从自回归模型和最小 Agent Loop 出发，逐层解释 Harness、上下文、记忆、RAG、Tool、Skill、工程选型与评测闭环为什么会出现。</description>
    </item>
  </channel>
</rss>
