Methodology

How we measure a website's readiness for AI agents, honestly and reproducibly.

What "agentic readiness" means

An AI agent has to read a page the way a machine does: through the accessibility tree, structured data, and discovery files, not through a rendered screenshot. Agentic readiness measures how well a site supports that, plus the trust signals an agent (or a person) weighs before transacting. Our checks mirror Google's Lighthouse "agentic browsing" scoring.

How we score

Like Lighthouse, we do not emit an invented 0-100. Each page is measured against 30 deterministic checks; every check passes, partially passes, or fails based on the site's real HTML and discovery files. The headline is a fraction of passed checks. Where a signal cannot be assessed from available data, we say so - we never guess.

The checks

Agent interaction

• semantic html
• clean html
• extraction friction
• indexability
• layout stability
• canonical url
• document weight
• critical path efficiency

Machine extraction

• table list extractability
• sentence atomicity
• entity density
• definition patterns
• answer capsule pattern

Structured data

• schema markup
• schema coverage
• speakable schema

AI discovery

• llms txt
• robots txt
• sitemap completeness
• rss feed
• internationalization signals
• content licensing

Trust & transparency

• entity consistency
• creator transparency
• methodology transparency
• ai disclosure
• visible date signal
• title meta quality
• content freshness
• author schema depth

Data sources & provenance

Checks are computed from the site's own homepage and its discovery files (llms.txt, robots.txt, sitemap.xml). Every figure on a report is a verifiable fact about the live site. Each report shows a "last checked" date, and that date is what drives the page's freshness signal in our sitemap.

Trust & legitimacy signals

Alongside technical readiness we surface longevity (how long a site has been seen online, as a defensible lower bound), current activity, secure transport, and identifiable technology - the signals that indicate a real, maintained business rather than a throwaway site.

Ownership verification & linking policy

Site owners can verify ownership of their domain for free, by proving control via a DNS TXT record, a homepage meta tag, or a well-known file. Verification is re-checked periodically, and every owner edit re-proves control.

• Unverified profiles mention the subject domain as plain text and carry no outbound links - we do not link to sites nobody has vetted.
• Verified profiles carry exactly one outbound link: to the verified domain's homepage. Verification is our editorial vetting step; the link states that a real owner has proven control and confirmed the record.
• The link is never reciprocal. Verification does not require linking to MarkosWeb, displaying our badge, or anything else in return. The optional badge snippet we provide links here with rel="nofollow" by design.
• Owner-provided facts (organization, description, category, founding year) are shown with explicit provenance and never alter measured check results.