<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Maximilian Fabian Kirchner</title><description>Writing about agents and software engineering.</description><link>https://maximilianfabian.dev/</link><item><title>Testing Claude in Chrome, Claude Desktop and the Codex app’s browsers on the same job</title><link>https://maximilianfabian.dev/blog/built-in-browsers-for-agents/</link><guid isPermaLink="true">https://maximilianfabian.dev/blog/built-in-browsers-for-agents/</guid><description>I ran the browser job from my agent-browser, Playwright and Chrome DevTools study with the four browsers that come with Claude’s and Codex’s own apps, and compared every run with that study’s.</description><pubDate>Sun, 08 Nov 2026 00:00:00 GMT</pubDate><category>agents</category><category>browsers</category></item><item><title>Testing agent-browser, Playwright and Chrome DevTools with Claude Code and Codex</title><link>https://maximilianfabian.dev/blog/browser-tools-for-agents/</link><guid isPermaLink="true">https://maximilianfabian.dev/blog/browser-tools-for-agents/</guid><description>I had Claude Code and Codex do a browser job with agent-browser, Playwright and Chrome DevTools, over each tool’s CLI and its MCP server, and measured every run’s tokens and time.</description><pubDate>Sun, 01 Nov 2026 00:00:00 GMT</pubDate><category>agents</category><category>browsers</category></item></channel></rss>