Prompt Set
A prompt set is the fixed list of real questions you run across AI engines to measure your visibility, the stable foundation that makes citation tracking comparable over time.
Also known as: query set, tracking prompts
A prompt set is the questions you measure against, held constant. It's the curated list of real, high-intent queries your customers ask AI — the inputs you run repeatedly across engines to see whether you're mentioned or cited. Every visibility metric, from share of voice to citation share, is computed over a prompt set.
Its quality decides whether your measurement means anything, which is the alignment pillar applied to tracking: choose the questions that actually drive your business, phrased the way people really ask them. And it has to stay fixed — comparability over time is the whole point — so you can tell real movement from noise, the adaptability discipline. Aim for 15–30 questions weighted toward buying decisions, and expand it deliberately rather than churning it.
Example. A prompt set for an accounting tool might include "best accounting software for freelancers," "QuickBooks alternatives," and "is [brand] worth it" — run weekly across ChatGPT and Perplexity so the trend in who gets cited is measured on identical questions each time.
Relevant pillars
Related terms
- Share of Voice (AI)Share of voice in AI search is the proportion of relevant AI answers in which your brand appears, measured across a fixed set of questions, as a gauge of how present you are in the conversation.
- Citation ShareCitation share is the percentage of AI answers to your target questions in which your site is specifically cited as a source, the strictest measure of whether you're winning the citation, not just being mentioned.
- Answer EngineAn answer engine is a search system that responds to a question with a direct, synthesized answer instead of a list of links, usually citing the sources it drew from.