# Query fan-out

> Query fan-out is Google's term for the related sub-queries its AI features issue in parallel to gather more supporting pages for an answer. Google documents the technique. It warns that producing separate pages for fan-out variations to manipulate rankings or AI responses violates its scaled content abuse policy.

- URL: https://geo.casa/ai-search/query-fan-out/
- Concept · Officially documented
- Reviewed: 2026-10-25

## Definition

> **Officially documented:**
> Google defines query fan-out as "a set of concurrent, related queries generated by the model to request more information and fetch additional relevant search results to address the user's query." Its example: for "how to fix a lawn that's full of weeds", fan-out queries might include "best herbicides for lawns", "remove weeds without chemicals" and "how to prevent weeds in lawn".
>
> Sources: [Google Search Central: Optimizing your website for generative AI features on Google Search](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide)

> **Officially documented:**
> Both AI Overviews and AI Mode "may use" query fan-out. It issues related searches across subtopics and data sources. Google says this lets it show a wider and more diverse set of supporting links than a classic web search.
>
> Sources: [Google Search Central: AI features and your website](https://developers.google.com/search/docs/appearance/ai-features)

## What it implies for a site

A page can be cited for a sub-question the user never typed. Covering a topic's sub-questions in genuinely useful pages therefore matters more than matching the original query string.

## What not to do

> **Officially documented:**
> Google's scaled content abuse spam policy covers separate content for every possible variation of how people might search, including fan-out queries. Creating it primarily to manipulate rankings or generative AI responses is a violation. Google also calls it "an ineffective long-term strategy".
>
> Sources: [Google Search Central: Optimizing your website for generative AI features on Google Search](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide)

## What has been measured

> **Research-backed:**
> A University of Toronto study (October 2026) replayed its questions through the engines' APIs. Every page ChatGPT cited was one its own search had retrieved, and that search used sub-queries the model rewrites on every answer. For all of an answer's queries, 97% of the pages ChatGPT retrieved were absent from Google's top 50 and 99% from Bing's top 30, as were 93% of the pages Gemini cited, although Gemini is grounded on Google Search. The websites of 51% of ChatGPT's pages did appear in Google's top 50, so the engines often pick different pages from the same websites.
>
> Sources: [Chen and Koudas (University of Toronto), arXiv:2610.15033: What Drives AI Citations? Content, Retrieval and Model Knowledge in Generative Engine Optimization (GEO) (10 Oct 2026)](https://arxiv.org/pdf/2610.15033)

This is one study of two markets. It describes ChatGPT and Gemini, not Google's own fan-out.

## Not established

- Which fan-out queries Google generates for a given query. Google does not publish them, and they are not reported in Search Console.
- Whether other AI search products document a comparable technique. Their documentation does not describe one in these terms, though the study above observed ChatGPT rewriting each question into new sub-queries.

## Related

- [Google AI Overviews](https://geo.casa/ai-search/google-ai-overviews/) — where fan-out is used.
- [Generative Engine Optimization (GEO)](https://geo.casa/foundations/geo/) — the broader practice.

## Sources

- [Google Search Central: Optimizing your website for generative AI features on Google Search](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide)
- [Google Search Central: AI features and your website](https://developers.google.com/search/docs/appearance/ai-features)
- [Chen and Koudas (University of Toronto), arXiv:2610.15033: What Drives AI Citations? Content, Retrieval and Model Knowledge in Generative Engine Optimization (GEO) (10 Oct 2026)](https://arxiv.org/pdf/2610.15033)