https://tedfactory.com/en/tags/chrome-devtools/Recent content in Chrome DevTools on Ted FactoryHugoenSun, 26 Jul 2026 14:45:44 +0900https://tedfactory.com/en/notes/essays/giving-agents-a-browser/Sat, 25 Jul 2026 00:00:00 +0900https://tedfactory.com/en/notes/essays/giving-agents-a-browser/<h1 id="the-two-walls-you-hit-when-you-hand-an-agent-a-browser">The Two Walls You Hit When You Hand an Agent a Browser<a class="anchor" href="#the-two-walls-you-hit-when-you-hand-an-agent-a-browser">#</a></h1> <p>2026-07-25</p> <p><img src="https://tedfactory.com/images/notes/giving-agents-a-browser-cover.png" alt="Handing an agent a browser" /></p> <p>One principle I hold onto when delegating work to coding agents: if the agent changed the code, the agent should verify the result itself. For a web project, that means opening a browser and looking at the screen. For this I use MCP (Model Context Protocol, the standard for connecting external tools to agents) servers such as <a href="https://github.com/ChromeDevTools/chrome-devtools-mcp" target="_blank">chrome-devtools-mcp</a> and <a href="https://github.com/microsoft/playwright-mcp" target="_blank">Playwright MCP</a>. The agent launches Chrome, opens pages, clicks around, takes screenshots, and validates its own work.</p>