DocsFeature guides

Fan-outs

The real web-search queries an AI assistant ran while answering your prompts — lifted verbatim from the stored payload, ranked by estimated demand, and trackable in one click.

A fan-out is a real web-search query an AI assistant actually ran while answering your prompt, lifted verbatim from the stored answer payload — never simulated. Fan-outs show you the searches that genuinely shaped an answer.

What it does

When an engine answers a prompt, it often runs its own web searches first. MentionFlow captures those queries from the stored payload and surfaces them so you can see the demand behind your topics — and turn any query into a prompt you track directly.

How to use it

Open Fan-outs to see a table of the captured queries. Each row shows:

  • The query as the assistant ran it, with a verbatim badge when the assistant searched your prompt word-for-word (an echo of the prompt rather than an expansion of it).
  • An estimated AI volume for the query.
  • The engines that ran it and the answer count it appeared in.
  • The triggering prompts — which of your prompts caused the search.
  • A one-click Track, which creates a tracked prompt from the query.

Tracking a fan-out creates a normal prompt, so it counts against your pooled prompt quota like any other.

How it's computed

Queries are aggregated by their lowercased key over the selected window, with echoes (verbatim repeats of your prompt) sorted after true expansions, and the list is capped at the top 100. Each run contributes up to 20 queries.

Estimated volume comes from a DataForSEO AI-search-volume lookup backed by a three-tier cache. A string that can't be measured coerces to an em-dash — "no data", not zero — following the data-honesty rule.

Untracked fan-outs also feed a fan-out-opportunity recommendation: a query qualifies when it has at least 2 runs and either an estimated volume of at least 100 or at least 4 runs.

Limits

Only engines that emit the search-query field in their payload populate this screen — today that is ChatGPT and Perplexity. Volume estimates require DataForSEO credentials; without them, every volume fails open to an em-dash rather than a guess.

  • Shopping demand — the same fan-outs, narrowed to shopping carousels and ranked Top / Trending / Losing / New.
  • Prompts — where a tracked fan-out becomes a monitored question.
  • Research — demand research that feeds the same suggestion pipeline.
  • Actions — where the fan-out-opportunity recommendation appears.