<?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>Architecture on ClawLearning</title><link>https://clawlearning.github.io/en/tags/architecture/</link><description>Recent content in Architecture on ClawLearning</description><image><title>ClawLearning</title><url>https://clawlearning.github.io/og-image.png</url><link>https://clawlearning.github.io/og-image.png</link></image><generator>Hugo</generator><language>en</language><lastBuildDate>Thu, 07 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://clawlearning.github.io/en/tags/architecture/index.xml" rel="self" type="application/rss+xml"/><item><title>Lesson 17: Anatomy of an Agent — the Pieces of the Puzzle</title><link>https://clawlearning.github.io/en/posts/lesson-17-agent-components/</link><pubDate>Wed, 22 Apr 2026 00:00:00 +0000</pubDate><guid>https://clawlearning.github.io/en/posts/lesson-17-agent-components/</guid><description>The components of an AI agent: brain, tools, memory, senses, and hands. How they fit together to create a working agent.</description></item><item><title>Lesson 28: Multiple Agents — When One Isn't Enough</title><link>https://clawlearning.github.io/en/posts/lesson-28-multiple-agents/</link><pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate><guid>https://clawlearning.github.io/en/posts/lesson-28-multiple-agents/</guid><description>When it makes sense to have more than one agent, how to organise them, and how to combine expensive and cheap models intelligently.</description></item></channel></rss>