# What is query fan-out, and why no tool can show you Google’s real fan-out queries

> Query fan-out is how AI search turns one question into many searches. What Google has said about it, what the data sold as “fan-out queries” really is, and how to write for it.

Canonical: https://crawlwise.site/guides/ai-search/what-is-query-fan-out
Last updated: 2026-10-29

Query fan-out is how AI search answers one question: the system splits it into several related searches, runs them, and builds one answer from the results. Google says AI Mode and AI Overviews may use it. Google does not publish the fan-out queries behind any answer, so a tool can only guess them.

by Adnan Arodiya

Updated October 29, 2026 · 7 min read

## Key takeaways

- Fan-out turns one question into several related searches whose results feed one answer.
- Google says AI Overviews and AI Mode “may use” it; Deep Search “can issue hundreds of searches.”
- Google does not publish the fan-out queries, and its generative AI report shows pages, not queries.
- Lists sold as “fan-out queries” are either one recorded answer from another engine, or generated guesses.

“Query fan-out” went from an engineering term to a marketing one in about a year. Ahrefs’ June 2026 trends report puts US searches for “query fan out” at about 450 a month, up 2,550% year over year. Some of what is written about it promises to show you the queries Google runs. This guide explains what fan-out is, what Google has actually said, and why nobody outside Google can show you its real fan-out queries.

## What is query fan-out?

Query fan-out is a way of answering one question with many searches. The system splits the question into related sub-questions, runs a search for each, and writes one answer from what comes back. Google’s AI optimization guide defines fan-out queries as “A set of concurrent, related queries generated by the model to request more information.” When Google introduced AI Mode on May 20, 2025, it said “AI Mode uses our query fan-out technique, breaking down your question into subtopics,” and that Deep Search “uses the same query fan-out technique but taken to the next level” and “can issue hundreds of searches.”

## Which AI search products use it?

For Google, the AI features documentation says AI Overviews and AI Mode “may use a ‘query fan-out’ technique — issuing multiple related searches across subtopics and data sources — to develop a response.” Note the “may”: not every answer fans out, and Google does not say how many searches a given answer used.

The same pattern shows up outside Google. In October 2025 the data provider DataForSEO added a `fan_out_queries` field to the ChatGPT answers it sells, describing it as search queries derived from the main question that ChatGPT uses to retrieve more information.

## What does fan-out look like? An illustration

Take the question “Is Crawlwise good for a small Shopify store?” A fan-out system might look up what Crawlwise is, the basics of Shopify SEO, what a small store needs from an audit, and how Crawlwise compares with other tools, then combine the results into one answer. **Those sub-questions are our illustration, written by hand.** They are not queries Google or ChatGPT reported running, and the real set behind any answer is not published.

## Can you see Google’s real fan-out queries?

No. Google does not list the fan-out queries behind an AI Overview or an AI Mode answer in Search Console or in any public report we know of. Its Search generative AI performance report, announced on June 3, 2026, shows how often your URLs appeared, by page, country, device and date; the announcement does not mention queries at all. That leaves two kinds of “fan-out” data you will see on offer:

- **Recorded queries from another engine.** When a provider buys a ChatGPT answer through an API, some APIs return the searches ChatGPT ran for that one answer. That is real data, but it is one answer, from one engine, at one moment — and it says nothing about Google.
- **Generated guesses.** A tool asks a language model to imagine the sub-questions a topic might fan out into. That can be good brainstorming. It is not a measurement of what Google ran, and a tool that presents it as one is overstating what it knows.

> A list of likely sub-questions is a writing aid. It becomes a false claim the moment it is labelled as the queries Google ran.
>
> Adnan Arodiya, Crawlwise

## What does the Crawlwise question planner do?

Our free [content question planner](https://crawlwise.site/tools/query-fanout) drafts the questions a page on your topic should answer, for a brief or an FAQ. It used to be called a query fan-out tool. We renamed it, because it writes editorial questions from the topic you type: it does not see the queries any engine runs, and it shows no search volumes. The tool page says that above the tool, not in the footer.

## How should fan-out change the way you write?

- **Cover the sub-questions on the page that owns the topic.** If people asking about your product also need pricing, setup time and limits, answer those on the page, under clear headings.
- **Answer each one plainly.** Start the section with the answer, then give the detail. A system pulling one passage for one sub-question then gets a passage it can use.
- **Link related pages.** Google lists “Making your content easily findable through internal links on your website” among its practices for AI features.
- **Do not make a page per guessed sub-question.** Thin near-duplicate pages were a problem before AI search and still are. Google’s guide puts it plainly: “Don’t just recycle what others on the internet have already said.”

Google also says fan-out helps it “identify more supporting web pages, allowing us to display a wider and more diverse set of helpful links.” In plain terms, a page that answers one sub-question well can be cited even if it would not rank for the question that was typed. For the wider picture, see [what GEO is](https://crawlwise.site/guides/ai-search/what-is-geo) and [how to show up in Google AI Overviews](https://crawlwise.site/guides/ai-search/how-to-show-up-in-google-ai-overviews).

## How Crawlwise tests this

The [content question planner](https://crawlwise.site/tools/query-fanout) drafts the questions to cover, labelled as editorial prompts rather than engine queries. A full [audit](https://crawlwise.site/) checks whether the page’s opening passage answers its question and whether the text is in the source HTML, which is what a retrieval system can quote. The free [AI Overview checker](https://crawlwise.site/tools/ai-overview-checker) shows whether a search returned an AI Overview when we checked; it cannot show the fan-out behind it, because nobody outside Google can.

Every check, what counts as a block, and what the checks cannot see are written up on the [methodology page](https://crawlwise.site/methodology).

## What a plan actually costs

The free tools stay free. You can open them, run them, and leave without an account. A plan is for the moment you want the report saved, a few sites watched, or the same checks from the API. The price on this table is the price at checkout. A yearly plan is ten months of the monthly price, so two months are on us.

| Plan | Monthly | Credits | A good fit when |
| --- | --- | --- | --- |
| Starter | $4.99 | 10 | You look after one site and check it now and then |
| Pro | $14.99 | 40 | A few sites, plus the API and a handful of watched URLs |
| Studio | $49.99 | 150 | Client work that would burn through Pro mid-month |
| Agency | $99.99 | 400 | Many locations, reported under your own name |

A single-page audit is about 1.25 credits, and that includes the live probe of answer-engine crawlers. You see the estimate before anything runs. If a hold is not used, it comes back to your balance. Extra credits, when you already subscribe, are $9.99 for 20.

## Frequently asked questions

### Is query fan-out the same as “People also ask”?

No. People also ask is a visible part of the results page, with questions Google chose to show. Fan-out is an internal step in building an AI answer, and Google does not publish the queries it generates.

### Do fan-out queries have a search volume?

Not one anyone can measure. They are generated by the model for a single answer. A keyword tool’s volume counts what people typed, which is a different thing.

### Can I optimize for one specific fan-out query?

Not reliably, because you cannot see them. Cover the sub-questions your readers actually have, on the page that owns the topic, and answer each one plainly.

### Does ChatGPT fan out too?

Data providers that buy ChatGPT answers report the searches ChatGPT ran for each answer, which shows the same pattern for that engine.

## Sources

Every page below was read on 2026-10-29. Vendors change prices, limits and documentation without notice, so check the original before you act on a detail.

- [Google Search Central — AI optimization guide](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)
- [Google — AI in Search: Going beyond information to intelligence (May 20, 2025)](https://blog.google/products/search/google-search-ai-mode-update/)
- [Google Search Central Blog — Introducing Search Generative AI performance reports in Search Console (June 3, 2026)](https://developers.google.com/search/blog/2026/06/gen-ai-performance-reports)
- [DataForSEO — Fan-out queries in the ChatGPT LLM Scraper endpoint (October 29, 2025)](https://dataforseo.com/update/fan-out-queries-in-llm-scraper-endpoint)
- [Ahrefs — 10 SEO trends I’ve seen firsthand in 2026 (Ryan Law, June 18, 2026)](https://ahrefs.com/blog/seo-trends/)

## Crawlwise question planner vs writing the questions by hand

| What you get | Crawlwise | By hand |
| --- | --- | --- |
| Drafts a question list from a topic | Yes, in seconds | Yes, in an hour or so |
| Shows the queries Google actually ran | No, and the tool says so | No |
| Knows the exact words your customers use | No | Yes, from sales calls and support tickets |
| Claims a search volume | Never | Only with a keyword tool |

## Meet the author

Adnan Arodiya

Crawlwise

Writes about what Crawlwise actually measures: on-page evidence, crawler access, and performance signals — with the limits stated up front.

## Related guides

[What is GEO? Generative engine optimization vs SEO vs AEO, explained simply](https://crawlwise.site/guides/ai-search/what-is-geo): GEO, AEO and SEO describe overlapping jobs. Here is what is genuinely new, and what is the same work with a new name.

[How to get your website mentioned by ChatGPT: what you can control and what you can’t](https://crawlwise.site/guides/ai-search/how-to-get-mentioned-by-chatgpt): Four things you can control, three you cannot, and how to check where you stand without guessing.

[How to show up in Google AI Overviews: what Google requires, recommends and reports](https://crawlwise.site/guides/ai-search/how-to-show-up-in-google-ai-overviews): Google says there are no extra requirements for AI Overviews. Here is what that means in practice, and how to measure it.