What is AI Share-of-Voice (SoV)?

AI Share-of-Voice is the percentage of category prompts whose answers name your brand, relative to all brands named in those answers, measured per engine and averaged across the engines that actually answered. It is a count of real mentions in real answers divided by the total real mentions, expressed as a percent — no weighting by who pays, no adjusted score, no proprietary multiplier.

Does RadRank invent competitor names?

No. RadRank surfaces only names that appear verbatim in an engine's answer text, matched after normalizing case and whitespace. It never infers a likely competitor, never lets a language model guess a brand, and never adds a name the engine did not say. If an answer names no brands, the result is an empty list.

Does RadRank have access to real ChatGPT or Perplexity user queries?

No. RadRank measures answers to a disclosed, synthetic prompt set and does not claim access to any private stream of real user queries. It gives a repeatable, transparent, apples-to-apples benchmark — the same prompts, the same extraction rule, the same engines, run on a cadence for every brand in a category.

What happens when an engine does not answer?

The result stamps which engines actually answered and SoV is averaged only across those. An engine that did not answer is reported as absent — never silently counted as a zero. RadRank will never say 'across 4 engines' if only 2 answered.

RadRank Methodology — how the AI-answer score is made

01What AI Share-of-Voice actually means

AI Share-of-Voice (SoV) is the percentage of category prompts whose answers name you, relative to all brands named, measured per engine, then averaged across the engines that actually answered. For a single engine:

We send a set of realistic, neutral category prompts.
For each answer, we extract every brand name the engine actually wrote down.
Your SoV for that engine is the share of brand-mentions across those answers that are you. If ten answers name brands forty times and you are named six times, your SoV for that engine is 15%.
We repeat per engine and average across the engines that returned an answer.

That is the entire calculation. No weighting by who pays us, no "adjusted" score, no proprietary multiplier. SoV is a count of real mentions in real answers, divided by total real mentions, expressed as a percent.

02The prompt set

RadRank ships a small, disclosed default prompt set for each category. The defaults are short (eight words or fewer), realistic (phrased the way a person actually asks an assistant), neutral (they ask the question; they do not lead toward an answer), and disclosed (the exact prompts we run are shown to you — nothing is hidden).

You can — and should — add your own real prompts. The closer the prompt set is to how your customers actually ask, the more useful the number. We do not claim the default set is exhaustive; we claim it is honest, repeatable, and the same for everyone in your category.

03The engines, and honest engine stamping

RadRank queries multiple AI engines. Not every engine answers every time — keys expire, rate limits hit, an engine declines a prompt. When that happens, we tell you.

The result stamps engineMode and lists exactly which engines actually returned an answer.
SoV is averaged only across engines that answered. An engine that did not answer is reported as absent — never silently counted as a zero.
We will never write "across 4 engines" if only 2 answered. The stamped count always equals the number of real, non-null engine results.

If two engines answered, the page says two engines answered. This is a hard rule, not a preference.

04Citation extraction: only names that are really there

When we read an answer to find the brands it names, we surface only names that appear verbatim in the answer text.

Every brand we attribute to an answer is a literal substring of what that engine wrote (matched after normalizing case and whitespace).
We never infer a competitor "that's probably also relevant." We never let a language model complete or guess a likely-sounding brand. We never add a name the engine did not say.
If an answer names no brands, the result is an empty list — not a plausible filler name.

Refused in code

We would rather show an honest gap than invent a number — or a name — that makes anyone look more or less beatable than they are. This is enforced in the extractor, not just promised in copy.

05Show the receipt

Every score links to its evidence. For each engine and each prompt you can see the exact prompt sent, the raw answer text the engine returned, and the brand names we extracted from it. Nothing about the score is asserted without the underlying answer you can read yourself. If a mention is in your count, you can point to the sentence that earned it.

06Sandbox / sample mode

If no engine keys are configured, or a daily spend cap is reached, RadRank does not invent a result to fill the gap. Instead it returns a clearly labeled sample (mode: 'sandbox'). Sample cards are visibly marked "sample" and fabricate no metric — there is no real-looking SoV or rank presented as a measurement. A sample shows you the shape of the report; it never pretends to be your report.

07The honest fault line: synthetic vs. real

This is the most important thing on the page, so we state it plainly. RadRank measures answers to a disclosed, synthetic prompt set. We do NOT claim access to a private stream of real user queries. We do not have a backdoor into ChatGPT's, Perplexity's, or anyone else's live traffic, and we will never imply that we do.

What RadRank gives you is a repeatable, transparent, apples-to-apples benchmark: the same prompts, the same extraction rule, the same engines, run on a cadence, for every brand in a category. That repeatability is the value. A number you can reproduce and audit is worth more than a number we ask you to trust.

In one sentence: RadRank counts, per engine and only across the engines that answered, the real brand mentions in real answers to disclosed prompts — shows you the receipts — and never invents a name, a number, or a query stream it does not have.

Next: read the Neutrality Pledge → · or check your RadRank →