<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI Agents on AI VOID</title><link>https://ai-blog.noorshomelab.dev/categories/ai-agents/</link><description>Recent content in AI Agents on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 17 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/categories/ai-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Adding Logic and Control Flow with Lua in AIPack</title><link>https://ai-blog.noorshomelab.dev/aipack-guide-2026/lua-logic-control-flow/</link><pubDate>Sun, 17 May 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/aipack-guide-2026/lua-logic-control-flow/</guid><description>&lt;h2 id="introduction-beyond-static-prompts"&gt;Introduction: Beyond Static Prompts&lt;/h2&gt;
&lt;p&gt;So far, you&amp;rsquo;ve learned how to define multi-stage AI agents using markdown within AIPack. These agents are powerful for sequential tasks, but what happens when your agent needs to make a decision? What if it needs to retry an action or branch its behavior based on an AI model&amp;rsquo;s output or an external condition? Pure markdown, while excellent for prompt templating, lacks the dynamic control flow needed for truly intelligent and resilient agents.&lt;/p&gt;</description></item></channel></rss>