Unit-testing AI Agents in the Browser - Browserbase - Headless Web Browser API
Instead of trying to evaluate every aspect of an AI agent, we can focus on a simpler question: "Given a specific instruction like "click the button", was the expected button clicked?"
https://www.browserbase.com/blog/unit-testing-ai-agents-in-the-browser?dub_id=PL46FdtqBoQTyCCb