Agent Readiness Compare

Lighthouse Agentic Browsing category (Chrome)

Audit or test tool operated by Google Chrome (Lighthouse).

In short

An experimental Lighthouse category, run in Chrome 150 or later, that audits a page for machine interaction with deterministic checks and reports a pass ratio instead of a 0 to 100 score. 6 sourced facts follow, each with its read date.

What it is

An experimental Lighthouse category, run in Chrome 150 or later, that audits a page for machine interaction with deterministic checks and reports a pass ratio instead of a 0 to 100 score.

Operator: Google Chrome (Lighthouse). Type: Audit or test tool. Home page: developer.chrome.com/docs/lighthouse/agentic-browsing.

Ten-criterion rubric

Lighthouse Agentic Browsing: every scored part of the ten-criterion rubric, read 5 November 2026
CriterionPointsWhat the source says
Journey: find4 of 4ARD manifest audit 1
Journey: read4 of 4llms.txt and accessibility tree audits 1
Journey: use4 of 4WebMCP tool and schema audits, layout stability 1
Journey: pay0 of 3no payment audits 1
Checks2 of 157 audits are listed for the category (three WebMCP, llms.txt, ard.json, accessibility for agents, layout stability); under the 10-check band 1
Real agents0 of 15deterministic audits, no agent run 1
Open method: catalog3 of 3each audit has a documentation page 1
Open method: weights0 of 3no weighted score by design 1
Open method: scale0 of 2pass ratio, no grade scale 1
Open method: changes2 of 2scoring page dated 5 May 2026 1
Standards: cites1 of 32 of its 7 agentic-browsing audits link the spec they test: the ard.json audit page links the ARD spec and the llms.txt audit page links llmstxt.org; the three WebMCP audit pages link none, and the two audits on accessibility and layout stability link web.dev articles, not specs (29 percent) 2
Standards: maintains2 of 2Google is named on agentready.org as a collaborator on the AgentReady standard 3
Dev fit: api3 of 3runs as a Node module for programmatic use; there is no hosted API 4
Dev fit: mcp0 of 3no MCP server or tool is named on the Lighthouse pages; WebMCP is an audit target 1
Dev fit: cli2 of 2Lighthouse CLI 1
Dev fit: ci2 of 2called suitable for CI/CD 1
Peers: ranking0 of 6none
Peers: size0 of 4none
Fixes: guidance4 of 4each audit page explains the fix 5
Fixes: brief0 of 3each audit page explains its own fix; no single brief or prompt 1
Fixes: applies0 of 3none
Repeat scans1 of 5calls the audits deterministic and lists causes of fluctuation; no data 1
Free: free3 of 3free and open source 1
Free: limits2 of 2no cap 1

Total 39 of 100, rank 7 of 10. The ranking is on the pick page; the same cells are on the evidence page.

What the sources say

  • The Agentic Browsing category evaluates how well a site is constructed for machine interaction through a set of deterministic audits.6
  • Unlike other Lighthouse categories it has no weighted average score from 0 to 100; the report shows a fractional score (how many agentic readiness checks pass), pass or fail status for specific audits and informational counts.6
  • The category and its WebMCP support are marked experimental and based on proposed standards; testing it requires Chrome 150 or later, and WebMCP audits require registering for the WebMCP origin trial.6
  • Its audits cover WebMCP tool registration (declarative and imperative tools, read through the Chrome DevTools Protocol WebMCP domain), a subset of accessibility audits (names and labels, tree integrity, visibility), Cumulative Layout Shift, the presence of llms.txt at the domain root, and an ard.json manifest.6
  • The ard.json audit looks for an Agentic Resource Discovery manifest through an Agentmap directive in robots.txt, a rel="ard" link, a Link header or /.well-known/ard.json, falls back with a warning to ai-catalog.json, and validates it against a JavaScript port of the ARD v0.91 conformance suite without fetching the artifacts it points to.2
  • The documentation says results can fluctuate when tools are registered dynamically in JavaScript, when the accessibility tree changes, or when layout shifts move elements; it calls the audits suitable for CI/CD pipelines.6

What it does not do

  • Does not give a weighted 0 to 100 score or a ranking; the documentation says the focus is signals, not a definitive ranking.
  • Does not run an AI agent on a task; its audits are deterministic checks of the page.

Sources

  1. developer.chrome.com/docs/lighthouse/agentic-browsing/scoring. https://developer.chrome.com/docs/lighthouse/agentic-browsing/scoring, read 2026-11-05.
  2. developer.chrome.com/docs/lighthouse/agentic-browsing/ard. https://developer.chrome.com/docs/lighthouse/agentic-browsing/ard, read 2026-11-05.
  3. agentready.org/llms.txt. https://agentready.org/llms.txt, read 2026-11-05.
  4. developer.chrome.com/docs/lighthouse/overview. https://developer.chrome.com/docs/lighthouse/overview, read 2026-11-05.
  5. developer.chrome.com/docs/lighthouse/agentic-browsing/webmcp-schema-validity. https://developer.chrome.com/docs/lighthouse/agentic-browsing/webmcp-schema-validity, read 2026-11-05.
  6. Lighthouse Agentic Browsing docs. https://developer.chrome.com/docs/lighthouse/agentic-browsing, read 2026-11-05.

Last reviewed 2026-11-05