Google's Lighthouse tool adds "Agentic Browsing" audits to test how websites handle AI agents

Google is testing a new experimental category called "Agentic Browsing" in its Lighthouse analysis tool. The audit checks four areas: integration of Google's WebMCP API, the accessibility tree (the core data model for machines), visual stability via Cumulative Layout Shift (CLS), and presence of an llms.txt file.

Unlike classic Lighthouse tests, there is no 0–100 score; instead, developers receive a ratio of passed checks. The category is based on proposed standards that are not yet final.

In testing, Airbnb passed only one of three Agentic Browsing checks: the accessibility tree wasn't well-formed, the llms.txt fetch failed, and all WebMCP audits came back as not applicable. Google recommends developers use semantic HTML, proper ARIA labels, and minimize layout shifts to prepare pages for AI agent interaction.