<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Knowledge-Retrieval on Unbound Force</title><link>https://unboundforce.dev/tags/knowledge-retrieval/</link><description>Recent content in Knowledge-Retrieval on Unbound Force</description><generator>Hugo</generator><language>en-US</language><copyright>Copyright (c) 2025-2026 Unbound Force</copyright><lastBuildDate>Wed, 01 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://unboundforce.dev/tags/knowledge-retrieval/index.xml" rel="self" type="application/rss+xml"/><item><title>Your AI Agent Doesn't Read the Docs</title><link>https://unboundforce.dev/blog/dewey-knowledge-retrieval/</link><pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate><guid>https://unboundforce.dev/blog/dewey-knowledge-retrieval/</guid><description>&lt;h2 id="the-problem-with-training-data"&gt;The Problem with Training Data&lt;/h2&gt;
&lt;p&gt;When you use a framework, you keep the docs open in a browser tab. You check function signatures, read about new APIs, and verify that the patterns you remember are still current. You do this because libraries evolve — the &amp;ldquo;right way&amp;rdquo; to do something in React, Go, or TypeScript changes with each release.&lt;/p&gt;</description></item></channel></rss>