<?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>Claude on AI Coding Blog</title><link>https://mpklu.github.io/tags/claude/</link><description>Recent content in Claude on AI Coding Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 25 Apr 2026 12:00:00 -0400</lastBuildDate><atom:link href="https://mpklu.github.io/tags/claude/index.xml" rel="self" type="application/rss+xml"/><item><title>The Lie We Tell About the Code</title><link>https://mpklu.github.io/posts/living-knowledge-base/</link><pubDate>Sat, 25 Apr 2026 12:00:00 -0400</pubDate><guid>https://mpklu.github.io/posts/living-knowledge-base/</guid><description>&lt;p&gt;&lt;em&gt;Every codebase has two states: the code, and the lie we tell about the code. Most documentation systems make the lie comfortable. One I came across recently doesn&amp;rsquo;t.&lt;/em&gt;&lt;/p&gt;
&lt;hr&gt;
&lt;p&gt;Documentation has always been the thing engineering teams promise to do and quietly skip. Sprint deadlines win, the wiki rots, the README becomes archaeology. We all know the cycle.&lt;/p&gt;
&lt;p&gt;Recently I came across a project (by &lt;code&gt;Franco Dominguez Noriega&lt;/code&gt;) that does it differently — and the difference is not just &amp;ldquo;we tried harder this time.&amp;rdquo; It&amp;rsquo;s a structural change that only makes sense in a world where AI agents are part of the development loop. After spending some time with it, I&amp;rsquo;m convinced the pattern is worth sharing, because it solves the documentation-decay problem in a way I haven&amp;rsquo;t seen before.&lt;/p&gt;</description></item></channel></rss>