<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>AI on KubernetesLab</title><link>https://kuberneteslab.dev/en/categories/ai/</link><description>Recent content in AI on KubernetesLab</description><image><title>KubernetesLab</title><url>https://kuberneteslab.dev/images/og-brand.png</url><link>https://kuberneteslab.dev/images/og-brand.png</link></image><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 03 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://kuberneteslab.dev/en/categories/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Does switching CLAUDE.md to AGENTS.md slow Claude Code down?</title><link>https://kuberneteslab.dev/en/blog/agents-md-migration/</link><pubDate>Fri, 03 Jul 2026 00:00:00 +0000</pubDate><guid>https://kuberneteslab.dev/en/blog/agents-md-migration/</guid><description>Measured whether the two workarounds for migrating a project context file from CLAUDE.md to AGENTS.md (import and symlink) cost speed or tokens in Claude Code, across 5 model configurations and 210 runs. No penalty on either axis.</description></item><item><title>How well do Claude / Gemini / Codex CLI agents handle Kubernetes incidents? (AIOps Agent Benchmark)</title><link>https://kuberneteslab.dev/en/blog/aiops-agent-benchmark/</link><pubDate>Wed, 27 May 2026 00:00:00 +0000</pubDate><guid>https://kuberneteslab.dev/en/blog/aiops-agent-benchmark/</guid><description>We compared nine model configurations across Claude Code, Gemini CLI, and Codex CLI on identical Kubernetes operations scenarios, and walked through the scoring decisions and what the results actually reveal. The headline: a higher tier is not always better.</description></item></channel></rss>