<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>Agent on Rost Glukhov | AI Systems &amp; Infrastructure</title>
		<link>https://www.glukhov.org/tags/agent/</link>
		<description>Recent content in Agent on Rost Glukhov | AI Systems &amp; Infrastructure</description>
		<generator>Hugo</generator>
		<language>en-us</language>
		
		
		
		
			<lastBuildDate>Sat, 24 Oct 2026 00:00:00 +0000</lastBuildDate>
		
			<atom:link href="https://www.glukhov.org/tags/agent/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>Decision LLMs: When a Model Should Decide — and When It Shouldn&#39;t</title>
				<link>https://www.glukhov.org/ai-systems/architecture/decision-llms-when-models-should-decide/</link>
				<pubDate>Sat, 24 Oct 2026 00:00:00 +0000</pubDate>
				<guid>https://www.glukhov.org/ai-systems/architecture/decision-llms-when-models-should-decide/</guid>
				<description>&lt;p&gt;Ask practitioners what breaks in agent systems and the answer is rarely capability. The failure is quieter: the model decides, and nobody can tell sound from fluent.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
