<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agent Loop on ByF (BaiFan) · Daily Deep Think</title><link>https://blog.baifan.site/en/tags/agent-loop/</link><description>Recent content in Agent Loop on ByF (BaiFan) · Daily Deep Think</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>blog@baifan.site (ByF (BaiFan))</managingEditor><webMaster>blog@baifan.site (ByF (BaiFan))</webMaster><copyright>CC BY-NC 4.0</copyright><lastBuildDate>Thu, 07 May 2026 09:00:00 +0800</lastBuildDate><atom:link href="https://blog.baifan.site/en/tags/agent-loop/index.xml" rel="self" type="application/rss+xml"/><item><title>The Soul of an AI Coding Assistant: The Think-Act-Observe Loop</title><link>https://blog.baifan.site/en/claude-code-think-act-observe-loop/</link><pubDate>Thu, 07 May 2026 09:00:00 +0800</pubDate><author>blog@baifan.site (ByF (BaiFan))</author><guid>https://blog.baifan.site/en/claude-code-think-act-observe-loop/</guid><description>&lt;!-- more --&gt;&#10;&lt;p&gt;If you dig through the Claude Code source, you will discover a counterintuitive fact:&lt;/p&gt;&#10;&lt;p&gt;&lt;strong&gt;The core of the entire program is a while loop.&lt;/strong&gt;&lt;/p&gt;&#10;&lt;p&gt;Not a complex state machine, not an elaborate pipeline, not distributed coordination — just a plain &lt;code&gt;while&lt;/code&gt; loop that does three things over and over: let the model think, let the model act, feed the results back.&lt;/p&gt;&#10;&lt;div class="highlight-wrapper"&gt;&lt;div class="highlight"&gt;&lt;div class="chroma"&gt;&#10;&lt;table class="lntable"&gt;&lt;tr&gt;&lt;td class="lntd"&gt;&#10;&lt;pre tabindex="0" class="chroma"&gt;&lt;code&gt;&lt;span class="lnt"&gt;1&#10;&lt;/span&gt;&lt;span class="lnt"&gt;2&#10;&lt;/span&gt;&lt;span class="lnt"&gt;3&#10;&lt;/span&gt;&lt;span class="lnt"&gt;4&#10;&lt;/span&gt;&lt;span class="lnt"&gt;5&#10;&lt;/span&gt;&lt;span class="lnt"&gt;6&#10;&lt;/span&gt;&lt;span class="lnt"&gt;7&#10;&lt;/span&gt;&lt;span class="lnt"&gt;8&#10;&lt;/span&gt;&lt;span class="lnt"&gt;9&#10;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/td&gt;&#10;&lt;td class="lntd"&gt;&#10;&lt;pre tabindex="0" class="chroma"&gt;&lt;code class="language-text" data-lang="text"&gt;&lt;span class="line"&gt;&lt;span class="cl"&gt;while (user hasn&amp;#39;t quit) {&#10;&lt;/span&gt;&lt;/span&gt;&lt;span class="line"&gt;&lt;span class="cl"&gt; thinking = callLLM(conversation history + tool definitions)&#10;&lt;/span&gt;&lt;/span&gt;&lt;span class="line"&gt;&lt;span class="cl"&gt; if (thinking.wants to call a tool) {&#10;&lt;/span&gt;&lt;/span&gt;&lt;span class="line"&gt;&lt;span class="cl"&gt; result = executeTool(thinking.toolCall)&#10;&lt;/span&gt;&lt;/span&gt;&lt;span class="line"&gt;&lt;span class="cl"&gt; conversationHistory.push(result)&#10;&lt;/span&gt;&lt;/span&gt;&lt;span class="line"&gt;&lt;span class="cl"&gt; } else {&#10;&lt;/span&gt;&lt;/span&gt;&lt;span class="line"&gt;&lt;span class="cl"&gt; output(thinking.reply)&#10;&lt;/span&gt;&lt;/span&gt;&lt;span class="line"&gt;&lt;span class="cl"&gt; }&#10;&lt;/span&gt;&lt;/span&gt;&lt;span class="line"&gt;&lt;span class="cl"&gt;}&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/td&gt;&lt;/tr&gt;&lt;/table&gt;&#10;&lt;/div&gt;&#10;&lt;/div&gt;&lt;/div&gt;&#10;&lt;p&gt;That&amp;rsquo;s it? The entire secret of an AI coding assistant lives in this loop?&lt;/p&gt;</description></item></channel></rss>