# Maximilian Fabian Kirchner > Writing about agents and software engineering. The studies among the posts measure how tools for coding agents perform, and the guides help a reader choose tools and run the work. Each link below is the Markdown copy of a page on https://maximilianfabian.dev, with the page’s text, its tables and each chart as text. The page itself is at the same address without index.md. Each copy ends with the page’s citation, in a sentence and in BibTeX. ## Posts - [Testing Claude in Chrome, Claude Desktop and the Codex app’s browsers on the same job](https://maximilianfabian.dev/blog/built-in-browsers-for-agents/index.md): 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. - [Testing agent-browser, Playwright and Chrome DevTools with Claude Code and Codex](https://maximilianfabian.dev/blog/browser-tools-for-agents/index.md): 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.