Glossary

Prompt sampling

Prompt sampling, also called synthetic sampling, is the method of measuring AI visibility by running a fixed set of buyer questions against AI assistants on a schedule, many times each, and analyzing the answers for brand mentions, positions and citations. It is the only data source available, because real conversations between users and assistants are private.

What a good sample looks like

Fifteen to twenty-five prompts phrased the way buyers ask, without the brand name in them, run daily in clean conditions with no memory or custom instructions. Ten answers per prompt and engine is the floor before a percentage means anything.

What it can and cannot tell you

It tells you, with real statistical footing, what the assistants tend to say when asked and which sources shape those answers. It cannot tell you what real users asked, how many people heard an answer, or what a personalized assistant said to any one person.

Prompt-set discipline

Changing the prompt set changes every number. Keep the set fixed while periods are compared, and when it changes, mark the date on the timeline so the discontinuity is not read as a trend.

Read more

Measure it for your brand

CitePrism computes every metric in this glossary from scheduled samples across seven engines, with the raw answers one click away. Free to start with your own keys.