{"version":1,"type":"story","url":"https://digestai.news/story/google-lighthouse-13-5-adds-audit-for-ai-agent-resource-discovery","json":"https://digestai.news/story/google-lighthouse-13-5-adds-audit-for-ai-agent-resource-discovery.json","markdown":"https://digestai.news/story/google-lighthouse-13-5-adds-audit-for-ai-agent-resource-discovery.md","slug":"google-lighthouse-13-5-adds-audit-for-ai-agent-resource-discovery","headline":"Google Lighthouse 13.5 adds audit for AI agent resource discovery","summary":"Google’s Lighthouse 13.5 release adds an experimental audit for Agentic Resource Discovery (ARD), a proposed specification that tells AI agents how to locate an organization’s tools and services. The audit checks a site’s robots.txt for an Agentmap line, a link tag with the ai-catalog relation, and the HTTP Link header; if none are found it falls back to requesting /.well-known/ai-catalog.json. Schema errors or an unloadable catalog cause the audit to fail, while the absence of any pointer results in a “Not Applicable” status.\n\nThe update will appear in Chrome 156 DevTools and is slated to roll out to PageSpeed Insights within two weeks of the release. The ARD spec, now at version v0.91, recommends the manifest file /.well-known/ard.json, but Lighthouse still looks for the older ai-catalog.json path. The specification remains a proposal and credits Junjie Bu (Google), R.V. Guha (Microsoft) and Shaun Smith (Hugging Face). The audit is part of Lighthouse’s “Agentic Browsing” category, which shows a pass ratio rather than a 0‑100 score because the standards are still emerging.","keyPoints":["Lighthouse 13.5 audit checks robots.txt, link tag, HTTP Link header, then /.well-known/ai-catalog.json for an ARD catalog.","Audit will be available in Chrome 156 DevTools and PageSpeed Insights within two weeks of release.","ARD spec v0.91 now prefers /.well-known/ard.json, but Lighthouse still looks for the older ai-catalog.json path."],"whyItMatters":"The audit gives web owners a way to verify AI‑agent discoverability, helping early adoption of emerging agentic web standards.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Google","Microsoft","Hugging Face"],"models":[],"people":["Junjie Bu","R.V. Guha","Shaun Smith"]},"firstPublishedAt":"2026-09-21T14:32:33Z","updatedAt":"2026-09-21T14:32:33Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"Search Engine Journal","title":"Google Lighthouse Adds Audit For AI Agent Resource Discovery via @sejournal, @MattGSouthern","url":"https://searchenginejournal.com/google-lighthouse-ai-agent-resource-discovery-audit/590274","publishedAt":"2026-09-21T14:32:33Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Google Lighthouse 13.5 adds audit for AI agent resource discovery\", 21 September 2026, https://digestai.news/story/google-lighthouse-13-5-adds-audit-for-ai-agent-resource-discovery","publisher":"Digest AI","title":"Google Lighthouse 13.5 adds audit for AI agent resource discovery","datePublished":"2026-09-21T14:32:33Z","url":"https://digestai.news/story/google-lighthouse-13-5-adds-audit-for-ai-agent-resource-discovery"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}