<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Playwright on Blowing in the wind</title>
    <link>https://zheng-bobo.github.io/en/tags/playwright/</link>
    <description>Recent content in Playwright on Blowing in the wind</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <lastBuildDate>Sat, 12 Sep 2026 21:06:45 +0200</lastBuildDate>

  <atom:link href="https://zheng-bobo.github.io/en/tags/playwright/index.xml" rel="self" type="application/rss+xml" />


    <item>
      <title>Anthropic Agent Evolution III: The Planner–Generator–Evaluator Quality Loop</title>
      <link>https://zheng-bobo.github.io/en/post/anthropic-agent-evolution-3-planner-generator-evaluator/</link>
      <pubDate>Sat, 12 Sep 2026 21:06:45 +0200</pubDate>

      <guid>https://zheng-bobo.github.io/en/post/anthropic-agent-evolution-3-planner-generator-evaluator/</guid>
      <description>&lt;p&gt;The first harness let an agent continue across context windows, but continuity is not quality. Generators routinely mistake “mostly runs” for “good enough,” especially in subjective product and design work.&lt;/p&gt;

&lt;p&gt;Anthropic&amp;rsquo;s next step separated planning, generation, and evaluation so that an external evaluator became a source of evidence the generator had to respond to.&lt;/p&gt;</description>
    </item>

  </channel>
</rss>