CitePulse — Methodology

How we measure whether AI cites you

Most AI-visibility tools give you a percentage and ask you to trust it. We publish the rule. Our detection is deterministic and our share-of-voice denominator is disclosed, so you can reproduce the number and see exactly what it does and doesn't cover.

1. The questions we ask

We don't test vanity brand queries. For each domain we generate real buyer questions in its category ("best X for Y", "how do I switch from Z"), grounded in the site and industry, then freeze that set so every re-run is a like-for-like comparison. The free mini-audit runs 5 questions × 3 repetitions per engine; the full audit runs 20 (or 40 in deep mode). We repeat each question because AI answers vary between runs, and we average to smooth that out.

2. The detection rule (the part nobody else publishes)

For every answer, a brand counts as cited when either is true:

your brand token (≥4 chars, whole-word) appears in the answer text
    — OR —
your domain appears in the answer's cited sources

It is a literal string match, not an AI judging another AI. There is no hidden "confidence" model deciding whether you were mentioned. Anyone can re-run the same question and check the same rule.

Per-engine citation rate = cited repetitions ÷ total repetitions, for each engine. Your composite score (0–100) is the average of those per-engine rates across every engine that returned at least one valid answer.

3. Citation Share, with the denominator shown

Citation Share answers: of all the sources the AI engines cited for your buyer questions, what share is yours vs a competitor's vs everyone else's? We show the full denominator — total source citations, split self / competitor / other — because an unstated denominator is an unverifiable metric.

Citation Share = your cited sources ÷ all cited sources (self + competitor + other)

3b. "Seen in k of n runs" and the two doors (DOORS-1.0)

One run is a snapshot, not a state. Published measurements from 2026 put day-to-day turnover of the sources AI engines cite at roughly two thirds, so we never present a single run's list of cited pages as "your pages". Every page we show carries seen in k of n runs, where n counts only comparable runs: the same frozen question set and the same measurement version. A free audit is n = 1 and is labelled as a single measurement.

For every buying question we also say which door is open. Door A: ordinary pages win the citations, or you are already cited, so your own page can compete. Door B: best-of lists, directories and marketplaces win, so the lever is being present on those pages, not rewriting your own. The rule is mechanical: a door is decided when at least two thirds of the distinct sources AI cited share one shape; anything in between is mixed; a question with no returned sources is unknown and stays out of the percentages. We read doors per phrasing and draw conclusions from the whole question set, because two paraphrases of one question overlap only weakly in what AI cites. We never claim you are absent from a third-party page; we show which pages win and leave the check to you.

3c. How much the engines move on their own (NOISE-1.0)

No vendor publishes this number, so we measure it ourselves, in public. Every day we ask the four engines the same five frozen buying questions about our own site (citepulse.ai), three times each, and record how much the answers differ from one repetition to the next and from one day to the next. Nothing here enters any score. It exists so that every "before / after" we show a client is read against how much the engines move by themselves.

• Noise band — median absolute change in citation share per question, day over day. A change smaller than the band is "within normal variation".
• Repetition agreement — share of questions where three repetitions on the same day gave the same cited / not-cited result.
• Source overlap day to day — median Jaccard similarity of the set of cited URLs for a question between consecutive days.

Last panel run: 2026-09-06. Engines below 14 measured days show the default band with their day count; the measured band replaces it automatically at day 14. Values refresh daily.

4. Which engines count, and where

• Mini-audit (free): ChatGPT, Perplexity, Gemini — plus Google AI Overviews as a source.
• Full audit: adds Claude — 4 scored engines.
• Monitoring — Shield: ChatGPT, Perplexity, Gemini.
• Monitoring — Protect & Scale: add Grok — 4 engines tracked.

Across the whole product a brand can be measured on up to 5 assistants — ChatGPT, Perplexity, Gemini, Claude and Grok. Protect and Scale share the same engine coverage; the difference between them is agency features, not assistants.

5. The honest limits

• Citation Share counts the sources engines actually return. Perplexity, Gemini and Google AI Overviews surface their sources on nearly every answer. ChatGPT and Claude surface them only when they run a live web search, so their per-engine source counts vary from run to run — and can be zero on a given run. The denominator always discloses the exact per-engine breakdown, so it stays verifiable rather than hidden. Every engine is also covered by the per-engine citation rate in section 2, which reads the answer text directly.
• String matching under-counts, never over-counts. A paraphrase that never names your brand, or a mention with no link, can be missed. We would rather report a mention we can prove than infer one we can't.
• Answers shift. AI output changes with retrieval and model temperature, which is why we repeat questions and track deltas over time on frozen prompt sets.
• No one can guarantee a citation. Not us, not any agency, not the model vendors. We measure signals; we never promise an outcome.

Check your own

Run a free mini-audit: https://api.citepulse.ai

Results reflect AI output at evaluation time and vary between runs. Correlation, not causation: a change in your citations is not proof any single action caused it. A product of GeoFlow Solutions Marcin Gamża.