Skip to content
Vercatus

What Vercatus does

Most of your audience now reads an answer before they read your site. That answer was assembled by a machine that fetched your pages, split them into passages, ranked them against a question, and decided whether to cite you. Vercatus reproduces that pipeline against your own site so you can see it fail before it fails in public.

We call what it measures machine readership: machines are now a readership of your site, with their own reach, comprehension and citation behaviour, and like any readership they can be measured. Three layers, each a number that repeats from run to run:

  • Reach — the share of pages each machine identity can obtain, and whether it gets the page a person gets.
  • Understanding — the entities and evidenced claims a machine extracts, and the questions it can answer from them.
  • Citability — the share of questions in your field that a retrieval engine over your own passages answers completely.

What a run produces

Section titled “What a run produces”

Point Vercatus at a sitemap. One run:

  1. Maps the site — every URL in the sitemap index, clustered by template and language, then sampled so each pattern is represented. A few hundred pages can speak for a million.
  2. Fetches each page as several machines — a plain HTTP client, a real browser, a browser with JavaScript disabled, Googlebot, and five AI crawlers — and compares what each was served. See Machine identities.
  3. Builds a knowledge graph — entities resolved across pages and linked to Wikidata, factual claims scored for specificity and evidence, and the questions each page can answer. See Entities and claims.
  4. Simulates the answer — a retrieval engine over your own passages answers each question in your intent space and judges whether the answer was complete and grounded. See The retrieval simulation.
  5. Reviews and ranks — specialist analysis is checked by an adversarial reviewer that discards anything unsupported. What survives is ranked by impact against effort, each item naming the metric and the pages to measure it on. See Findings.

Every finding cites the knowledge base hypotheses it rests on, graded from official documentation to practitioner consensus.

What it is not

Section titled “What it is not”

Vercatus is not a rank tracker, a keyword tool or a technical checklist. It will not tell you a heading is too long. It will tell you that the template holding your category definitions returns 403 to every AI crawler while your robots.txt says they are welcome — and what to measure in two weeks to confirm the fix worked.

Where to go next

Section titled “Where to go next”