The retrieval simulation

Answer engines do not read pages; they retrieve passages. Vercatus builds the same shape of pipeline over your own content so you can see which questions it fails on.

The simulation is three stages of a run (index, intents, simulate); How a run works puts them in the sequence.

The index

Each page’s main content is split into heading-aware passages. Passages are indexed for both exact terms and meaning, in every language the site uses, so a run of ten thousand pages retrieves as cheaply as one of ten. This is the hybrid shape production retrieval systems use, and it fails the same way they do: passages that depend on context, restate a subject with a pronoun, or bury the answer in the fourth paragraph do not retrieve.

The intent space

The questions the site should win. With analysis agents on, it is generated from the site’s own profile and each page’s answerable questions, deliberately including comparison, alternative, troubleshooting and sub-question intents that sites rarely write headings for. Without agents, it is derived from headings and titles. That is enough to run the simulation, but weaker as a test.

The verdict

Each intent is retrieved. With agents on, a model answers from the retrieved passages only and judges: was the question fully answered, was every statement grounded in the passages, what was missing, and did two pages supply the same support (cannibalisation). Without agents, the verdict comes from retrieval scores alone and is coarser.

What comes out

• Coverage by intent class: where the site systematically cannot answer (commercial and comparison questions are the usual gaps).
• Gaps: for each partial or unanswered intent, what a complete answer needed. This is the content roadmap, derived from retrieval rather than from a keyword tool.
• Cannibalisation: intents where several of the site’s own pages compete with near-equal passages.
• Never retrieved: content pages that no intent reaches, which usually means their passages are not written in a way retrieval can match to a question.
• Cross-language leakage: a query in one language answered by another language’s page although the site publishes in the query’s language.

What it is not

It is a model of retrieval, not a measurement of any live engine. Real engines add ranking signals, freshness and source-credibility weighting that this simulation does not. Treat its verdicts as predictions. What the live engines do is the poll’s job, and whether a change worked is a verdict’s.

Where it leads

A topic with demand that no page on the site answers becomes a Write the missing page play. When the simulation drew on a page for a partial answer, and the question falls within what that page is for (its title, headings and the searches the run read it as meant to answer), the play asks to update that page, with the gaps the simulation named. A question that fits no page gets a page of its own, so a privacy notice that mentions your product never takes a buyer’s question. A gap the simulation finds on an existing page also becomes evidence on a Fix a page play. See Plays.