Query fan-out
Query fan-out is the process by which an AI engine turns one user question into several search queries, runs them, and composes its answer from the combined results. It means a page competes for the queries the engine writes, which often add words the user never typed, rather than for the user's original wording.
How it works
In an illustrative case, a question such as "what is the best CRM for a small agency" becomes separate searches for a ranked list, for pricing, for reviews and for comparisons between named products. The engine reads the top results for each search and writes one answer from them. The citations under the answer come from those searches.
Why it matters
The cited page is the page that answers a fanned-out query well, not necessarily the page that matches the question. Engines often add a year, "pricing", "reviews" or a use case to the searches they run. A clear pricing page or an honest comparison can earn citations for questions it never mentions.
Seeing the queries
Some engines report the queries they ran while answering, and some do not. Where an engine exposes them, CitePrism records the queries per prompt on its Queries page. Where it does not, the cited sources are the next best evidence of what it searched for.