Skip to content

Free tool

AI visibility calculator: range, answers needed and gaps.

Enter how many answers named you and how many you collected. You get the 95% range around your rate, the answers a narrower range needs, and whether a gap with a competitor, or a change since last month, is larger than chance.

Calculator

Your answers

named ÷ answers

Every answer you counted, named or not.

Your rate

95% Wilson range

30.2%

range 24.2–37.0% · from 192 answers

0255075100

Your true rate is very likely between 24.2% and 37.0%. A report that says “30%” without that range claims more than 192 answers can show.

Your target

smallest count that fits

Your last result, or 30 if you have none yet.

5 means a range of about ± 5 points.

Answers you need

95% Wilson range

320answers

for a range of ± 5 points around 30%

  • ± 10 points78 answers
  • ± 5 points320 answers
  • ± 3 points894 answers

Halving the margin takes roughly four times the answers.

Your answers

on the same answers

For a change over time, enter this run as you and the last run as them, on the same questions and engines.

The gap

95% range of the difference

9.9points

them ahead · range 1.9 to 17.9 points

You 30.2% · Them 40.1% · on the same 192 answers

A clear gap. The range excludes zero.

The calculation runs in your browser. No sign-up.

Reading it

How to read your result

Your range

58 of 192 answers is a rate of 30.2%, range 24.2–37.0%. The range is where your true rate very likely sits, given the answers you have. “Very likely” means 95%: across many measurements made this way, about 19 in 20 ranges contain the true rate.

95% range at a 30% rate, by number of answers
AnswersRange at a 30% rate
1010.8–60.3%
3016.7–47.9%
5019.1–43.8%
10021.9–39.6%
20024.1–36.7%
40025.7–34.7%
1,00027.2–32.9%

Answers you need

A range of ± 5 points around 30% takes 320 answers. ± 10 points takes 78, and ± 3 points takes 894: halving the margin roughly quadruples the answers. Plan the questions, engines and repeats to reach that count in each run.

Gap or change

A gap is clear only when its range excludes zero. On 192 answers where 21 named only you, 40 only them and 37 both, they lead by 9.9 points, range 1.9 to 17.9: a clear gap. With 28 only you, 33 only them and 30 both, they lead by 2.6 points, range −5.5 to 10.7: no clear gap, because the range includes zero.

The same tab reads a change over time: enter this run as “you” and the last run as “them”, on the same questions and engines. Is that change real? works through examples.

Method

How it calculates

  • Your range is the Wilson score interval at 95% (E. B. Wilson, Journal of the American Statistical Association 22 (158), 209–212, 1927, doi:10.1080/01621459.1927.10502953), the interval AmpliRank reports with every rate. It stays sensible near 0% and 100%, where the textbook “± 2 standard errors” gives impossible ranges.
  • Answers you need is the smallest number of answers whose Wilson range at your expected rate is no wider than the margin you asked for.
  • Gap or change compares the two rates on the same answers, answer by answer. That is more precise than comparing two separate ranges, because the questions and engines both sides faced are the same.
  • One simplification: the calculator treats each answer as independent. Answers to the same question tend to agree, so a full run report can show a wider range. Use the calculator to plan and to sanity-check a number.

The method page explains how AmpliRank reports ranges, gaps and changes in a run.

Next step

Your real rate, measured the same way.

AmpliRank asks AI answer engines the questions your buyers ask, and reports every rate with this range, competitors on the same answers, and the searches and sources behind each answer.

■ Ask · Measure · Compare · Trace · Fix · Share

See what AI says about you.

Cookies