← Back to articles
Google's Lighthouse tool adds "Agentic Browsing" audits to test how websites handle AI agents
THE DECODER · May 21, 2026
AI Summary
- •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.
Related Articles
Large Language Models
Alphabet's net profit surged 44% to $160 billion on a trailing-12-month basis, driven by AI-powered Search and growing Google Cloud profitability.
Yahoo Finance AI·May 23, 2026
Large Language Models
Nvidia CEO says $200 billion CPU market forecast includes China amid U.S.-China tensions
Yahoo Finance AI·May 23, 2026
Large Language Models
Alibaba's Qwen3.7-Max AI model ran autonomously for 35 hours to optimize code for its own custom chip, achieving a 10x speedup
THE DECODER·May 23, 2026
Large Language Models
Google releases Omni Flash, a video generation model that improves consistency and real-world knowledge over its predecessor Veo
The Verge AI·May 23, 2026
Large Language Models
Anthropic's Claude Mythos Preview finds over 10,000 critical vulnerabilities faster than teams can patch them
THE DECODER·May 23, 2026
Stay ahead with AI news
Get curated AI news from 200+ sources delivered daily to your inbox. Free to use.
Get Started Free