<?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>Context Engineering on FisherAI</title>
    <link>https://fisherdaddy.com/tags/context-engineering/</link>
    <description>Recent content in Context Engineering on FisherAI</description>
    <image>
      <title>FisherAI</title>
      <url>https://fisherdaddy.com/images/papermod-cover.png</url>
      <link>https://fisherdaddy.com/images/papermod-cover.png</link>
    </image>
    <generator>Hugo -- 0.125.7</generator>
    <language>en</language>
    <lastBuildDate>Mon, 21 Jul 2025 19:24:55 +0800</lastBuildDate>
    <atom:link href="https://fisherdaddy.com/tags/context-engineering/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>AI 代理的上下文工程：构建 Manus 的经验教训 • Peak</title>
      <link>https://fisherdaddy.com/posts/context-engineering-for-ai-agents-lessons-from-building-manus/</link>
      <pubDate>Mon, 21 Jul 2025 19:24:55 +0800</pubDate>
      <guid>https://fisherdaddy.com/posts/context-engineering-for-ai-agents-lessons-from-building-manus/</guid>
      <description>本文系统总结了在构建 Manus AI 代理过程中围绕“上下文工程”的一系列实践经验，包括 KV 缓存设计、工具遮蔽、文件系统作为外部记忆、复述操控注意力、错误保留、避免少样本诱导等策略。适合开发者和研究者了解现代 AI Agent 的上下文建模方法。</description>
    </item>
  </channel>
</rss>
