VisibilityOS by PodPitch Read the research

AI audit sample size planner

Find out how many matched AI answers to compare when you want to estimate how often a brand mention or official link changes.

Set your assumptions

Use a pilot estimate or enter 50 if you're unsure.

For example, 10% plus or minus 5 points spans 5% to 15%.

Your collection target

139

matched pairs

That’s 278 saved answers if each answer is used in only one pair.

Your estimate139
If 50% of pairs change385

Budget for more runs if you expect missing answers or will repeat the same prompts.

How to use the target

Pick one outcome to track, such as a brand mention appearing or disappearing. A matched pair compares the same prompt, engine, settings and market across two collection rounds. Aim for a mix of distinct prompts. Repeated comparisons of the same prompts or adjacent days can be related and give you less information.

The VisibilityOS study observed 82 brand-presence changes across 817 matched pairs, about 10%. The calculator uses 10% as its starting assumption. Rates will vary across audits. See the study and method.

How the estimate works

For an expected rate p and margin e, both as decimals, round z² × p(1 − p) ÷ e² up to a whole pair. The confidence level sets z. This approximation assumes independent pairs and can be unreliable when few changed or unchanged pairs are expected. Use it as a planning estimate. NIST sample size guidance.

Build your audit plan
Track completed comparisons