Why AI Browser Agents Need a Runbook Before They Need More Prompts

<p>Your <strong>AI browser agent</strong> can open a page.</p> <p>It can click buttons.</p> <p>It can fill forms.</p> <p>It can even complete a workflow that looks correct from

<p>Most browser-agent demos still ask a capability question:</p> <blockquote> <p>Can the agent use the browser?</p> </blockquote> <p>That question made sense early on. A browser

<p>Your agent passed all the tests. It's been running in production for three weeks. And it has been quietly wrong the entire time.</p> <p>This is not a hypothetical. Galileo's

<p>The browser agent had one goal: check a set of public pages and return a structured result.</p> <p>The first page responded with <code>429 Too Many Requests</code>. The agent

<p>Most developers who build AI agents make the same mistake: they spend weeks designing the orchestration layer, tuning the system prompt, and picking the right model — then hand

<p>Everyone's building agents. Most are building them wrong. Not because they lack skill, but because they lack the right mental models. Before you write a line of code, you need

<p>Claude's context window holds 200,000 tokens. Gemini's stretches to two million. But response quality starts degrading long before the window fills up. Window size doesn't

<p>I've been using Ego Browser since it was released on GitHub. The useful idea is that an agent gets its own browser space while the human keeps their own browsing context.</p>