About this calculator
Real AI answers vary more than the 95% range assumes, so the true range is wider. By the formula below, at most 97 answers to one question bring the range within plus or minus 10 points.
How it decides
If you doubt a result, a spreadsheet can recompute it.
| Step | Rule | Where it comes from |
|---|---|---|
| Inputs | Answers collected: a whole number from 1 to 1,000. Answers that named you: a whole number from 0 up to answers collected. Anything else gets a message, not a result. | This calculator. |
| Rate and 95% range | p = named ÷ n and z = 1.96. Low = (p + z²/(2n) − z × √(p × (1 − p)/n + z²/(4n²))) ÷ (1 + z²/n). High is the same with + before z. If named is 0, low is 0%. If named equals n, high is 100%. All shown in whole percent. | Wilson score interval. Wikipedia prints the formula and says it can be used with small samples. Brown, Cai and DasGupta (2001) recommend it for small n. |
| Verdict on one rate | Width = high − low, in the whole points shown. More than 40: too few answers to say. 21 to 40: a rough range. 20 or less: a usable range, about plus or minus 10 points. | Our own cut-offs. |
| Answers needed for a margin | Write m and r as fractions: 10 points is m = 0.10, and 50% is r = 0.5. For a margin m at a true rate r, n = z² × r × (1 − r) ÷ m², rounded up. Worst case, r = 50%: margins of 5, 10, 15, 20 points need 385, 97, 43, 25 answers. At r = 10% and m = 10 points, 35 answers. | The standard formula for estimating a proportion, as on Wikipedia (its width W is 2m). |
| Check | Count entered | Result |
|---|---|---|
| One rate | 0 of 4 | 0% to 49%: too few answers to say |
| One rate | 2 of 5 | 12% to 77%: too few answers to say |
| One rate | 3 of 10 | 11% to 60%: too few answers to say |
| One rate | 6 of 20 | 15% to 52%: a rough range |
| One rate | 0 of 20 | 0% to 16%: a usable range, and zero stays inside it |
| One rate | 30 of 100 | 22% to 40%: a usable range |
What it cannot tell you
- Independence. Logged-in repeats can share history, so the true range is wider.
- Buyer wording. SparkToro's 142 prompts for one task barely resembled each other, yet brands such as Bose and Sony appeared in 55% to 77% of 994 answers.
- Cause. A name is not a recommendation, and a count does not say why. For visitors, see how to see whether AI sends you visitors and what AI assistants cite for local businesses.
Sources
| Source | What it says | Date | Who publishes it |
|---|---|---|---|
| SparkToro, AIs are highly inconsistent when recommending brands | Of 142 prompts that volunteers wrote for one task, barely two looked similar to the author. Running them returned 994 answers, and headphone brands such as Bose, Sony, Sennheiser and Apple appeared in 55% to 77% of them. | Published January 27, 2026. The survey requests ran in November and December 2025, and the post says newer models may differ. Read October 7, 2026. | SparkToro sells audience-research software. The study was run with a research partner who works at an AI tracking startup; the post says so. |
| Wikipedia, Binomial proportion confidence interval | The Wilson score interval formula, and that it can be used with small samples. | Page last edited September 11, 2026. Read October 7, 2026. | Wikipedia, a nonprofit encyclopedia. Sells nothing. |
| Brown, Cai and DasGupta, Interval estimation for a binomial proportion | The authors recommend the Wilson interval, or the Jeffreys interval, for small n. | Statistical Science, May 2001. Read October 7, 2026. | A statistics journal. Sells no AI tracking. |
| Wikipedia, Sample size determination | The sample size for estimating a proportion, with 0.5 as the most conservative rate. | Page last edited July 22, 2026. Read October 7, 2026. | Wikipedia, a nonprofit encyclopedia. Sells nothing. |
| Montrelia AI visibility scoreboard | Montrelia was named in 0 of 4 buyer questions in each of two runs on Ask Brave. | Runs on September 28 and October 2, 2026. | Montrelia, which sells GEO. One engine, our own measurement. |
Questions people ask
What does being named in 0 of 5 AI answers mean?
It means the true rate could still be as high as 43% (95% range, fresh sessions, one engine). Zero of 100 would still allow up to 4%. A zero never proves a business is never named; more answers only lower the ceiling.
Is AI visibility tracking accurate?
A tracker's percentage is only as accurate as the answer count behind it: the same 30% fits 11% to 60% from 10 answers and 22% to 40% from 100 (95% range, fresh sessions, one engine). Ask the vendor how many answers each percentage rests on and whether each was a fresh session.
Can I add up answers from ChatGPT, Gemini and Perplexity?
No. The 95% range holds for one question on one engine. If ChatGPT named you in 3 of 10 and Gemini in 1 of 10, pooling them as 4 of 20 gives 8% to 42%, which hides the difference between the engines. Enter each engine's count separately.
The other two checks
If you have two counts, from before and after a change, use the Did your AI visibility change? calculator.
If you are deciding how many answers to collect, use the AI answer sample size calculator.
Last updated October 7, 2026