Query Fan-Out
Query fan-out is the technique Google's AI Overviews and AI Mode use to split one search into several related sub-queries and build one answer from the combined results, so cited pages often don't rank for the original query.
Also known as: Fan-out queries, Sub-query expansion
Query fan-out is Google's term for what its AI does with your question before answering it. Instead of running the search you typed, it generates several related searches, runs them in parallel, and synthesizes the results into one response. Ask for the best pediatric dentist near Plano and the system might also search for pediatric dentist reviews Plano, dentists that take your insurance, sedation dentistry for kids, and Saturday hours. The answer draws from all of them.
This is why the old rule, rank on page one and you'll get cited, stopped holding. Ahrefs tracked 863,000 search results pages between July 2025 and March 2026 and found the share of AI Overview citations coming from pages ranking in Google's top 10 fell from 76% to 38%. Ahrefs attributes that drop directly to query fan-out. The pages being cited increasingly rank for one of the sub-queries, not the query the user typed.
Fan-out also explains why Google's two AI surfaces disagree with each other. Profound found AI Overviews and AI Mode cite the same URLs only 13.7% of the time. Both fan out, but AI Mode goes deeper and supports follow-up questions, so it ends up reading a different set of pages. Two Google products, one search box, mostly different sources.
For a small business, fan-out cuts both ways. The bad news is that a single well-ranked homepage no longer guarantees anything. The good news is that a specific page answering a specific sub-question, say a page on tankless water heater installation cost in your city, can get cited even though your site never ranked for the broad plumber query. Depth across the questions your customers actually ask beats one strong page.
Tibly's prompt generation reflects this. It builds buying questions from your trade and service-area cities, including the narrower variants a fan-out would produce, and tracks each engine's answer to each one. When the sub-question you're missing shows up as a content gap, Tibly can draft the page and publish it to your site.
Keep exploring the glossary
- Google AI ModeGoogle AI Mode is a conversational search experience inside Google Search that answers a question with a full AI-generated response, supports follow-up questions, and pulls its sources from many related searches rather than the single query you typed.
- AI OverviewsAI Overviews is Google's AI-generated summary that appears above the organic results for many searches, answering the query directly and citing a handful of sources instead of showing ten ranked links.
- Content Gap (AI answers)In AI visibility, a content gap is a buying question that AI engines answer by naming your competitors but not you, usually because your website has no page stating the specific service, price, location, or detail the engine needed.
- Prompt TrackingPrompt tracking is the practice of running a fixed set of buying questions against AI engines on a schedule, recording which businesses each answer names and which sources it cites, so visibility becomes a per-engine trend.
Common questions about Query Fan-Out
- Does query fan-out mean SEO rankings don't matter anymore?
- They matter less for AI citations than they did. Ahrefs found top-10 pages went from supplying 76% of AI Overview citations to 38% in eight months. Rankings still drive most traffic, since organic search is about 42.75% of website visits per Similarweb-family data, but they no longer buy an AI citation.
- How do I optimize for query fan-out?
- Publish pages that answer the specific sub-questions behind a buying decision: cost, timeline, service area, what's included, common problems. Each one is a candidate for a fan-out sub-query. A single broad services page gives the system one target; ten specific pages give it ten.
- Do ChatGPT and Perplexity use query fan-out too?
- Query fan-out is Google's name for its own technique, but the idea of issuing multiple searches to answer one question isn't unique to Google. Perplexity runs a fresh web search per query according to Profound, and other engines retrieve from several sources. Specific pages help across all of them.