<?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>Evals on FisherAI</title>
    <link>https://fisherdaddy.com/tags/evals/</link>
    <description>Recent content in Evals 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>Sun, 11 Jan 2026 12:04:21 +0800</lastBuildDate>
    <atom:link href="https://fisherdaddy.com/tags/evals/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>揭开 AI Agent 评估的神秘面纱 • Anthropic</title>
      <link>https://fisherdaddy.com/posts/demystifying-evals-for-ai-agents/</link>
      <pubDate>Sun, 11 Jan 2026 12:04:21 +0800</pubDate>
      <guid>https://fisherdaddy.com/posts/demystifying-evals-for-ai-agents/</guid>
      <description>Anthropic 工程团队分享了他们构建 AI Agent 评估体系的经验和最佳实践。</description>
    </item>
  </channel>
</rss>
