<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>SRE on Landry Zetam - Tech Blog</title><link>https://blog.landryzetam.net/tags/sre/</link><description>Recent content in SRE on Landry Zetam - Tech Blog</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Mon, 10 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.landryzetam.net/tags/sre/index.xml" rel="self" type="application/rss+xml"/><item><title>The Full Architecture of My Kubernetes Agents</title><link>https://blog.landryzetam.net/posts/kubernetes-agents-full-architecture/</link><pubDate>Mon, 10 Aug 2026 00:00:00 +0000</pubDate><guid>https://blog.landryzetam.net/posts/kubernetes-agents-full-architecture/</guid><description>&lt;p>Five agents run against my K3s cluster. Three of them form a closed loop — one detects problems, one fixes them, one reviews the fix — and none of the three can do another&amp;rsquo;s job. This is everything about how they&amp;rsquo;re built: the framework, the prompt assembly, every tool, both safety gates, the memory layers, and a real pull request one of them opened.&lt;/p>
&lt;p>Then I merged it and spent a day fixing what production found. Eight more bugs, none of them in the agent logic — §17 onward is that day, and it&amp;rsquo;s the more useful half.&lt;/p></description></item></channel></rss>