Free scan, no call needed4 AI engines checkedReport in 1 working dayCited in 90 days or next month free

Home / Glossary

AI search glossary

Prompt set

Prompt set
4AI engines tracked weekly
20Prompts in the free scan
1dayReport turnaround
90dCitation guarantee
In plain terms

Prompt set explained

Building it is a strategy exercise disguised as a list. Start with how buyers describe the problem, not how you describe the product. Add price qualifiers, city qualifiers, occasion qualifiers and competitor names, because that is how people actually type into a chat window.

A workable split for an Indian D2C brand is roughly forty percent category prompts, thirty percent comparison prompts, twenty percent problem prompts and ten percent brand prompts. Write them in the language the buyer uses, including Hinglish phrasing where that is genuinely common in the category.

Freeze the set before you start work, or you will end up measuring your own editing rather than your progress.

A prompt set is the fixed list of buyer questions used to measure AI visibility, run on the same schedule across the same engines so the results can be compared over time.

One definition is worth more than ten opinions

Every term here links to the service that owns the work and the tool that measures it.

Check it yourself

Three things you can test this week

None of these need a tool or a vendor. They take an afternoon and they tell you whether prompt set is actually your problem.

01
Take your top queries from Search Console and rewrite each as a person would type it into a chat window: longer, more specific, tied to a use case.
02
Add price, city, occasion and competitor qualifiers, because that is how buying questions actually arrive.
03
Freeze the set in writing before any work starts.

Our own measurement method, with its definitions and stated limits, is published on the method page.

4engines checked weekly
How we work

The definition is the easy part

Knowing what a term means takes five minutes. Knowing whether it is your problem takes an afternoon, and knowing what to do about it takes a method.

Every glossary page here ends with three checks you can run yourself and the primary sources behind them, because a definition you cannot act on is trivia.

Sources

Primary sources

Primary documentation for the mechanics described on this page. All published by the organisations that operate the systems in question.

Free scan See what ChatGPT, Gemini, Perplexity and AI Overviews say about your brand

Twenty buying prompts, four engines, you against three named competitors. Report in one working day. No call needed.

FAQs

Prompt set: common questions

Who writes the prompt set?

The brand and the agency together. Founders know the objections, the agency knows how engines parse phrasing.

How often should it run?

Weekly. Daily adds noise, monthly misses the movement.

Do prompts need to be in English?

Not always. If your buyers ask in Hinglish or a regional language, include those prompts, because answers and sources differ.

Free scan

See what the engines say about you

Twenty buying prompts, four engines, your brand against three named competitors. Report in one working day.

  • 20 buying prompts, your category
  • ChatGPT, Gemini, Perplexity, AI Overviews
  • You against three named competitors
  • Report in one working day, yours to keep
1 · Your brand2 · About you

No call needed. Report in one working day. Nothing is sent until step 2.

WhatsApp