See the searches behind an AI answer.
AI search engines split a question into several searches and build the answer from what they find. Enter a question and see the likely sub-queries, and which page would answer each one.
Do engines cite you for the original question?
The free report asks it, and up to four more, on ChatGPT, Gemini and Google AI Overviews, and shows who gets cited.
Measure it for freePaid plans track your questions every week and write articles that cover the missing angles. See plans
How this tool works
- Google has described “query fan-out” for AI Mode: the question is split into related searches that run at the same time, and the answer is built from the results. ChatGPT search and Perplexity also run several searches per question.
- We ask a small AI model to play that role and suggest the sub-queries, with the intent of each and the content that would answer it. Without the model, we use templates by intent.
- It’s free with limits: a few generations per connection per day and a daily budget for everyone. When they run out, you still get the template version.
- We don’t store your question; we only log the cost of the call, without the text.
Query fan-out questions.
What people ask before they start. If something’s missing, write to us.
Write to usWhat is query fan-out?
The technique AI search engines use to answer a question: they break it into several more specific searches (definition, comparisons, prices, reviews, location…), run them and combine what they find. The term comes from Google’s description of AI Mode.
Are these the exact searches ChatGPT runs?
No. No engine publishes them, and they change from one run to the next. These are plausible sub-queries, useful to check whether your content covers each angle.
What do I do with the list?
Check each sub-query against your site: if no page answers it clearly, that’s a gap. A comparison page, a pricing table or a “how to choose” guide often covers several at once.