<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agents on Derek's Guides</title><link>https://guides.derekleeds.cloud/categories/agents/</link><description>Recent content in Agents on Derek's Guides</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 15 Mar 2026 15:52:17 -0500</lastBuildDate><atom:link href="https://guides.derekleeds.cloud/categories/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>SEL × Cynefin: Security and Autonomy for AI Agents</title><link>https://guides.derekleeds.cloud/docs/security/sel-cynefin-framework/</link><pubDate>Fri, 13 Mar 2026 00:00:00 +0000</pubDate><guid>https://guides.derekleeds.cloud/docs/security/sel-cynefin-framework/</guid><description>&lt;p&gt;AI agents need to know two things before acting:&lt;/p&gt;
&lt;ol&gt;
&lt;li&gt;&lt;strong&gt;What tools can I use?&lt;/strong&gt; (Security Execution Level)&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;How autonomous can I be in this domain?&lt;/strong&gt; (Cynefin classification)&lt;/li&gt;
&lt;/ol&gt;
&lt;p&gt;This guide shows you how to implement both, with OpenClaw-specific examples and prompts.&lt;/p&gt;
&lt;h2 id="prerequisites"&gt;Prerequisites&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;OpenClaw installed and configured&lt;/li&gt;
&lt;li&gt;Basic understanding of AI agents&lt;/li&gt;
&lt;li&gt;Familiarity with &lt;a href="https://en.wikipedia.org/wiki/Cynefin_framework"&gt;Cynefin framework&lt;/a&gt;&lt;/li&gt;
&lt;/ul&gt;
&lt;h2 id="background"&gt;Background&lt;/h2&gt;
&lt;h3 id="the-problem"&gt;The Problem&lt;/h3&gt;
&lt;p&gt;When you have 150+ agents (like we do after installing Agency), you need answers to:&lt;/p&gt;</description></item><item><title>Memory Management Best Practices for AI Agents</title><link>https://guides.derekleeds.cloud/docs/memory-management/</link><pubDate>Thu, 12 Mar 2026 00:00:00 +0000</pubDate><guid>https://guides.derekleeds.cloud/docs/memory-management/</guid><description>&lt;p&gt;AI agents without memory are like developers without Stack Overflow - they start fresh every session, forget what they learned, and repeat the same mistakes. This guide shows you how to give your agents a working memory system.&lt;/p&gt;
&lt;h2 id="why-memory-matters"&gt;Why Memory Matters&lt;/h2&gt;
&lt;p&gt;When you build an AI agent, you quickly run into a basic problem: &lt;strong&gt;the model has no persistence between sessions&lt;/strong&gt;. Every conversation starts from zero. Every task requires re-explaining context. Every mistake gets repeated.&lt;/p&gt;</description></item></channel></rss>