<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Helm on SREKubeCraft | Nikos Nikolakakis</title><link>https://srekubecraft.io/tags/helm/</link><description>Recent content in Helm on SREKubeCraft | Nikos Nikolakakis</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 10 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://srekubecraft.io/tags/helm/index.xml" rel="self" type="application/rss+xml"/><item><title>Building a Read-Only Kubernetes Agent with Google ADK (Go)</title><link>https://srekubecraft.io/posts/kubernetes-agent-with-google-adk-go/</link><pubDate>Sun, 10 May 2026 00:00:00 +0000</pubDate><guid>https://srekubecraft.io/posts/kubernetes-agent-with-google-adk-go/</guid><description>&lt;p&gt;Every k8s incident I have watched in the last two years has the same opening five minutes: a senior engineer narrating &lt;code&gt;kubectl get pod&lt;/code&gt;, &lt;code&gt;kubectl describe&lt;/code&gt;, &lt;code&gt;kubectl logs --previous&lt;/code&gt;, while a junior engineer types it all into Slack. Same six commands, same order, every time. The work is mechanical; the context-switching is the cost.&lt;/p&gt;
&lt;p&gt;I wanted a small chat interface that could run those commands on my behalf and explain the output, without ever reaching for &lt;code&gt;kubectl delete&lt;/code&gt; or &lt;code&gt;exec&lt;/code&gt;. Not &amp;ldquo;AI ops&amp;rdquo;. Not a control plane. A read-only co-pilot for the boring 80% of triage.&lt;/p&gt;</description></item></channel></rss>