<?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>Bedrock on Ken Kitts</title><link>https://kenkitts.com/tags/bedrock/</link><description>Recent content in Bedrock on Ken Kitts</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 08 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://kenkitts.com/tags/bedrock/index.xml" rel="self" type="application/rss+xml"/><item><title>Building an AI Agent from Scratch, Part 1: What Even Is an Agent Harness?</title><link>https://kenkitts.com/posts/building-an-ai-agent-from-scratch-part-1-what-even-is-an-agent-harness/</link><pubDate>Mon, 08 Jun 2026 00:00:00 +0000</pubDate><guid>https://kenkitts.com/posts/building-an-ai-agent-from-scratch-part-1-what-even-is-an-agent-harness/</guid><description>LLMs can only produce text. So how do they &amp;#39;use tools&amp;#39;? Let&amp;#39;s break down the agent harness — the code that turns a language model into something that can actually do stuff.</description></item></channel></rss>