Methodology

Everything kwerve displays is recomputed from the raw answers we keep. This page explains how, so that every number in a report can be reproduced by hand.

What we measure

For each brand, a list of prompts is sent to each engine, several times over the period. Each send is one check: one prompt, one engine, one answer. The answer is then read to find the tracked brand and the declared competitors, and the position each of them appears at. Raw answers are kept: no number is estimated, all of them are recomputed from those answers.

The three metrics

Mention rate: The number of checks whose answer names the brand, divided by the number of successful checks. Failed calls are excluded from the denominator and counted separately.
Average position: The brand's mean position across the answers that name it. In each answer, its position is 1 plus the number of businesses listed before it (bold names and list items, whether declared competitors or not). Lower is better.
Share of voice: The brand's mentions divided by the total mentions of every tracked entity (the brand and the competitors you declared) across all answers in the period.

The AI visibility score (0 to 100)

What it is: how often and how prominently AI assistants recommend a business when its customers ask them. 0 means never named; 100 means named first in every answer, and as often as the most-cited competitor. It is built from the three metrics above:

The score is a deterministic weighted mean of three components, each normalised between 0 and 1, then multiplied by 100 and rounded once, at the end.

Mention rate (50%): the mention rate as it stands.
Average position (30%): 1 at position 1, falling linearly to 0 at position 5, as 1 − (average position − 1) ÷ 4. A brand never named scores 0.
Share of voice (20%): the brand's mentions divided by those of the most-mentioned entity. Level with the leader, the component is 1.

Share of voice is measured against the leader rather than as a raw percentage for a reason: a raw share falls mechanically as a category gains competitors. That would penalise a brand for its market rather than its performance.

Share of voice compares the business with the competitors declared for it. With none declared it is not shown, and the score is built from the mention rate and the position alone, their weights scaled to add up to 100%. Position does not need competitors: it counts every business an answer lists before this one.

A worked example

A brand named in 41 answers out of 106, at an average position of 3.46, with 41 mentions against the leader's 71:

Mention rate: 41 ÷ 106 = 0.387 → 0.387 × 50 = 19.34 points

Average position: 1 − (3.46 − 1) ÷ 4 = 0.385 → 0.385 × 30 = 11.55 points

Share of voice: 41 ÷ 71 = 0.577 → 0.577 × 20 = 11.55 points

Total: 42.44 → a score of 42 out of 100.

Every AI searches the web

Every AI we query searches the web before it answers, as it does for its own users: ChatGPT, Claude, Perplexity, Gemini and Grok. Their answers cite sources, and that is where the domains under “Cited sources” come from. Reports on periods before 22 September 2026 asked ChatGPT and Claude without web search; those reports say so.

What the score does not tell you

AI answers are not deterministic: two runs of the same question can differ. That is exactly why every prompt is repeated. A score compares only to itself, week on week, on the same prompt list and the same market, never across brands or categories. And nobody, kwerve included, can guarantee that an action will move a score up.

The weights above are the ones running in production today. If they change, this page changes with them.