Why do AI engines cite
one source over another?

Citation-probability model

The SCE-9.3 cross-encoder scores every (prompt, page) pair and returns a calibrated P(cite) — an honest probability, not a vanity score. Above a high-confidence threshold or below a low one it commits; the middle band is called an explicit toss-up.

Location-aware ranking

A prompt about Warsaw shouldn't be won by a Toruń-only page. Sorontai reads the page's real city from its domain, slug, title and entities, caps clear mismatches and boosts genuine local matches.

Best page per prompt

Given just a domain, it automatically finds the page that actually ranks for each query and scores that one — not your homepage against a pricing question.

SEE Evidence Map

Breaks the score down by page element — URL, title, entities, body — so you know exactly which one to fix first, and how much it's worth.

Measured AI visibility

Real ChatGPT / Perplexity / Gemini / Claude answers are captured for your prompts, so you see where the brand is cited, merely mentioned, or absent — with the competitors that win each answer.

Full-page content fetch

Sorontai fetches the page's real, rendered content — not just metadata — so every scoring factor reflects what's actually there. If your site blocks automated requests, allowlisting us takes a minute.

Gaps → action backlog

Every gap becomes a prioritized, evidence-backed action with acceptance criteria for the content team, exportable to Markdown or JSON.

Training export

New prompts and crawled pages accumulate for the next model round, exportable by date range — so the ranker keeps improving on your own market's data.

A full scored report, end to end

A real local-service audit rendered by the same engine that runs live: the AI-visibility score, per-prompt citation rankings, the SEE Evidence Map, gaps, the action backlog and measured-visibility layout. Nothing is uploaded and no site is crawled — it's a precomputed case so you can explore every tab.