Key takeaways
- Query fan-out means the AI model generates several related searches from your question, runs them at the same time and combines the results into one answer.
- Google uses it in AI Mode and says AI Overviews may use it too. Deep Search in AI Mode can issue hundreds of searches.
- For a business, it means your page competes on the sub-questions of a topic, not only on the main keyword.
- Answer the likely sub-questions inside strong pages. Google warns that mass pages built for fan-out queries can break its spam policy.
This guide explains query fan-out using only what Google has published, then turns it into a plan for your pages. It is part of the GEO hub; if you want the full how-to for appearing in AI Mode, read the Google AI Mode SEO guide.
What is query fan-out?
Query fan-out is a set of related searches that an AI model creates from one question, runs at the same time and uses to gather more results before it writes an answer. Google defines it as concurrent, related queries generated by the model to request more information. It is how AI Mode answers complex questions.
Google's July 2026 guide to generative AI features gives an example. For the question "how to fix a lawn that's full of weeds", the fan-out queries might include "best herbicides for lawns", "remove weeds without chemicals" and "how to prevent weeds in lawn". One question, three angles, each with its own search results. The final answer mixes what the model found in all of them.
How does query fan-out work in Google AI Mode?
When Google launched AI Mode on March 5, 2025, it said AI Mode issues multiple related searches at the same time across subtopics, then brings the results together into one response. In May 2025 Google added that it breaks your question into subtopics and issues a multitude of queries on your behalf. Deep Search can issue hundreds.
The launch post described AI Mode as running on a custom version of Gemini 2.0. Two months later, Google's May 20, 2025 update said Deep Search can issue hundreds of searches and create an expert-level, fully cited report in minutes. Google's AI features documentation adds that both AI Overviews and AI Mode may use fan-out across subtopics and data sources, and that while the answer is being written, its models find more supporting pages, which lets Google show a wider and more diverse set of links than classic search.
The scale is real: Google said in its I/O 2026 update that AI Mode had passed one billion monthly users. And the questions are long. In Pew's March 2025 data, searches with 10 or more words showed an AI summary 53% of the time, against 8% for one or two words.
A fan-out example for a business
The example below is hypothetical, written for this guide. The sub-questions are my guess at what a fan-out could include; Google does not publish the exact queries for a given answer.
| Customer question | Possible sub-question | Where your page should answer it |
|---|---|---|
| "Small business accountant in Houston who handles sales tax and payroll" | Accountant fees for small businesses in Houston | Pricing section with a range and what changes it |
| Texas sales tax filing deadlines | Short paragraph in the sales tax section, linked to the official source | |
| Accountant vs payroll software | An honest comparison: when software is enough | |
| Reviews of local accounting firms | Real reviews on your Business Profile and named credentials on the page |
One page from that firm could be cited for four searches, if it answers each of them clearly. A page that only repeats "best accountant in Houston" answers none of them.
What does query fan-out mean for your content?
It means coverage beats repetition. Because AI Mode searches the sub-questions of a topic, a page can be picked for a question it never targeted word for word. The pages that win answer the main question and the obvious follow-ups: price, timing, comparisons, risks and proof. Thin pages built around one keyword lose that race.
Google's guide says its systems can understand relevance even when there is no exact match between the query and the page's main content, and that you do not need to capture every variation of how someone might search. That is good news for small sites: a well-organized page that a buyer would find complete is what fan-out rewards. For how to write each answer, see how to write content for AI search.
How to plan pages for fan-out queries
- Pick one main question per page, the way a buyer would say it out loud.
- List the follow-ups a salesperson hears after that question: cost, time, options, risks, location and proof. Calls and emails are your best source.
- Group them: follow-ups that belong to the same decision go on the same page, each under a clear heading.
- Give bigger subtopics their own page only when they are a different decision, then link both pages to each other. A topic cluster is the classic way to organize this.
- Answer each sub-question in two or three sentences before the details, so any section can be quoted on its own.
- Test the main question in AI Mode every month and note which sources it cites for each part of the answer.
Should you create a page for every fan-out query?
No. Google's July 2026 guide says that creating separate content for every possible variation of how people search, including fan-out queries, mainly to manipulate rankings or AI responses, violates its scaled content abuse spam policy. It also says a high number of pages does not make a site higher quality. Answer sub-questions inside strong pages instead.
This is the trap many fan-out guides walk into: they turn each guessed sub-query into a thin page. That is the mass-page pattern Google's spam policies already cover, now aimed at AI. If a sub-question deserves its own page, it is because a buyer needs a full answer there, not because a tool listed it.
How can you see query fan-out in your data?
You cannot see the exact fan-out queries; the Google guides cited here do not list them for site owners. What you can see is the result: in Search Console, your pages getting impressions for searches they never targeted, and in AI Mode, which sources it cites for each part of an answer to your buyers' questions.
Keep a simple monthly log: the question, the parts of the answer, the sites cited for each part and whether yours is one of them. The gaps show which sub-question your page still does not answer well. My GEO plans include this testing every month, and the home page explains how I work.
Frequently asked questions
Does ChatGPT use query fan-out too?
This page covers Google, which names and documents the technique. Other assistants also run web searches before answering, but their exact methods are not described in the Google sources used here. That is why it pays to also answer the follow-up questions your buyers ask.
Is query fan-out the same as keyword research?
No. Keyword research finds what people search. Fan-out is what the AI searches on their behalf. Knowing your buyers' follow-up questions connects the two. That is why it pays to use both when you plan content. One finds topics, the other shapes answers.
Do AI Overviews use query fan-out?
Google's documentation says AI Overviews and AI Mode may both use the technique, across subtopics and data sources. That is why your pages should answer each subtopic clearly, in sections with their own heading and a direct answer. Link each section to related pages.
Can a tool show me the fan-out queries for my keyword?
Tools can guess likely sub-questions, but they are estimates. Google does not publish the exact queries behind a given answer. Use them as ideas, not exact data, and compare them with the questions your customers ask by phone, email or social media before you write a new page.
Does fan-out help small websites?
It can. Google says fan-out lets it show a wider and more diverse set of links than classic search, so a clear page on one sub-question has a chance to be cited. That is why it pays to write clear pages for each important subtopic.
Want to see these guides first? Choose JJ SEO Colombia as a preferred source on Google, and my articles are more likely to show up for you in Top Stories.
Follow on GoogleAdd as a preferred sourceSources
- Google, Expanding AI Overviews and introducing AI Mode (March 5, 2025)
- Google, AI in Search: Going beyond information to intelligence (Elizabeth Reid, May 20, 2025)
- Google Search Central, AI features and your website
- Google Search Central, Google's Guide to Optimizing for Generative AI Features on Google Search (updated July 10, 2026)
- Google, A new era for AI Search: Google Search's I/O 2026 updates (May 19, 2026)
- Pew Research Center, Google users are less likely to click on links when an AI summary appears (July 22, 2025)