Method

How the Agent Web Score is calculated

Each scan runs deterministic public checks across six dimensions. Dimension scores are severity-weighted pass rates, so failed high-impact checks pull the score down instead of merely shaving a few points from a perfect score.

Check weight

Critical, high, medium, and low checks count as 10, 7, 4, and 2 weight units.

Status credit

Pass earns full credit, warning earns half credit, and fail earns no credit.

Scope

Not-applicable, bonus, experimental, and info-only checks stay visible but do not affect the main score.

1. Discoverability

15% weight · 7 checks

Strong: robots, sitemap, canonical URLs and crawlable homepage signals.

2. Content Accessibility

20% weight · 6 checks

Mixed: HTML readability, markdown alternatives and heading structure.

3. Agent Access Policy

15% weight · 5 checks

Strong: robots policy, meta directives and low-risk fetch access.

4. Protocol Readiness

20% weight · 10 checks

Weak: MCP, WebMCP, Agent Skills, OpenAPI and well-known discovery.

5. AI Search Readability

15% weight · 4 checks

Strong: Organization, WebSite, FAQ and action-relevant structured data.

6. Task / Conversion Readiness

15% weight · 6 checks

Mixed: semantic CTAs, forms, demo, checkout and booking signals.

FAQ
Is this a Lighthouse score?

No. Lighthouse measures browser rendering and performance. Agent Web Score measures whether public signals support agent discovery, comprehension, and safe action.

Does the scan use a browser crawler?

No. It runs a bounded public quick scan across the homepage, response headers, robots.txt, sitemap.xml, /llms.txt, and fixed discovery paths. It does not perform deep crawling or authenticated testing.

Why can a site with many passes still score poorly?

The score is weighted by impact. Passing easy discovery checks helps, but missing protocol, content-accessibility, AI-search, or task-readiness signals can still keep the overall score low.

What grades map to the score?

A starts at 90, B at 80, C at 65, D at 50, and F below 50. A site also needs to avoid high or critical findings before it can be labeled Agent-friendly.

Why are reports public?

Public domain reports do not require an account or email gate, and they give teams a shareable URL for remediation work.