AI visibility (GEO)
AI Answer Sample-Size Calculator
Find how many AI answers you need to measure a mention rate within a margin of error, or the margin your answers give.
Runs in your browser; nothing is uploaded. · Free, no account · 3 min
Unsure? Keep 50: it is the most cautious choice.
Importing a saved run into your account is coming soon. Until then, your last runs stay in this browser only, and you can download your files.
How to use
- Choose whether you want the number of answers or the margin of error.
- Enter the mention rate you expect. If you have no idea, leave 50%, which needs the most answers.
- Enter the margin you accept, or the number of answers you have, and pick a confidence level.
- Optionally enter the number of engines and runs to see how many questions that implies.
What it checks and how it works
The calculator uses the normal approximation for a proportion: n = z² × p × (1 - p) / E², where z comes from the confidence level, p is the expected rate and E is the margin as a proportion. It is the standard sample-size formula for estimating a proportion, described in the statistics references below. At p = 50% it gives 9,604 answers for a margin of ±1 point at 95% confidence, and 385 for ±5 points.
It assumes every answer is an independent draw. Repeated runs of the same question are correlated, so many questions with a few runs each give more information than one question run many times. The figure is a planning number: the real uncertainty is wider when the answers are correlated, and it does not cover differences between assistants or markets unless you size each one separately.
Sources
- Wikipedia: Sample size determination (estimating a proportion) opened 29 Oct 2026
- NIST/SEMATECH e-Handbook of Statistical Methods: Sample sizes required for proportions opened 29 Oct 2026
Related tools
Mention-Rate Confidence Interval (Wilson)
Enter how many AI answers named your brand out of how many, and get the mention rate with a range you can defend.
Buyer Question Builder for AI Visibility
Turn your category, brand and one competitor into buyer questions for each funnel stage, in English and Arabic.
AI Answer Variability Across Runs (Jaccard)
Paste repeated answers to one question and see how much the set of brands named changes from run to run.
A/B Test Sample Size Calculator
Work out how many visitors an A/B test needs before you start, and roughly how many days that takes on your traffic.
Go further with Zaher: See how Zaher measures what AI says about your brand
Questions
About this tool
A rate near 50% has the most variation, so measuring it takes the largest sample. If you expect a rate near 10% or 90%, you need fewer answers for the same margin.
It is a new answer, but not an independent one, because the question and the market are the same. For a mention rate that stands for your category, use many different questions and a few runs of each.
Only if you collect that many answers from each one. The margin applies to the group of answers the rate is computed from. To compare two assistants, size each group on its own.
Get started today
Find out where your brand stands in AI. Free.
Run a free AI visibility analysis on your domain. No credit card, results in minutes. See what AI engines say about your brand today.
Brands already measuring their AI visibility with Zaher.
