Query Fan-Out: How AI Search Decomposes One Question Into Many

Query fan-out is the technique modern AI search systems use to answer questions. Instead of matching one query to one ranked list of pages, an AI engine takes the user's question, decomposes it into a multitude of sub-queries that cover different facets of the intent, retrieves relevant passages for each sub-query in parallel, then synthesizes one answer that cites the strongest sources.

Google named the technique publicly at I/O 2025: "AI Mode uses our query fan-out technique, breaking down your question into subtopics and issuing a multitude of queries simultaneously on your behalf." The same pattern is used by ChatGPT search, Perplexity, Microsoft Copilot and Gemini. Deep-research modes fan out further, into hundreds of sub-queries across many iterations, to assemble long reports.

The mechanism is described in Google's Thematic Search patent (US12158907B1), where sub-queries are called "themes." Independent research from Surfer SEO's December 2025 study of 173,902 URLs and iPullRank's technical breakdown documented eight distinct sub-query variant types: reformulations, related queries, implicit queries, comparative queries, entity-specific queries, personalized queries, recency queries, and disambiguations.

Classic search matched one page against one query. The page with the strongest links, on-page signals and freshness for that exact query won the click. Fan-out breaks that model. The shopper never sees the sub-queries, only the synthesised answer. The competition has moved underneath, where each sub-query is decided on its own and the best-matching passages get cited.

Surfer SEO's December 2025 study quantified the shift: 68 percent of pages cited by AI search do not appear in the top 10 organic results, and pages that match fan-out sub-queries see a 161 percent citation lift. The same study found sub-query stability of roughly 27 percent, meaning most of the sub-queries change when the same question is asked twice. There is no fixed list to optimise against. What matters is whether your content covers the underlying intent broadly enough that some passage matches whichever sub-queries fire.

In commerce, fan-out is the mechanism behind a common pattern: pages that rank well on Google while ChatGPT and Perplexity recommend a competitor. The pages that win classic rankings were written for one query. The products that win in AI answers are the ones whose attributes, schema and category content satisfy the most sub-queries. That is rarely the same page.

A buyer asks ChatGPT or Perplexity, "What is the best sunscreen for sensitive skin?" The shopper sees one answer with two or three product recommendations. Underneath, the AI engine has fanned out roughly twelve sub-queries: reef-safe formulation, mineral versus chemical UV filters, SPF rating and broad-spectrum coverage, fragrance-free options, pediatric-safe alternatives, dermatologist recommendations, ingredient lists for irritants, sensitive-skin specific testing, water resistance, application methods, comparable price points, and trusted brand citations.

Each sub-query is run in parallel against the AI engine's index. The engine retrieves the top-matching passages for each, weights them by source authority and freshness, and assembles a final answer that cites the products best supported across the most sub-queries. A retailer whose product page lists only "SPF 50, mineral, broad spectrum" satisfies maybe three of those twelve sub-queries. A retailer whose page also includes ingredient breakdowns, allergen flags, dermatologist-tested certifications, reef-safety certifications, and comparable-product context satisfies eight or nine. That second retailer gets the recommendation.

Critically, none of this depends on the literal phrase "best sunscreen for sensitive skin" appearing on the page. Fan-out optimizes for the underlying intent, not the surface keyword. This is also why classic SERP rank checks miss what AI search is actually rewarding.

The shift from classic SEO to fan-out-aware optimization changes the entire stack of decisions content and catalog teams make:

• Query length. Classic search queries averaged three or four words. Questions to an assistant run much longer because people explain their situation. Optimisation has to anticipate conversational intent.
• Unit of optimization. Classic SEO optimized at the page level. Fan-out retrieves at the passage level. Each H2 section needs to independently answer a distinct sub-query, with no sequential dependency on prior paragraphs.
• Authority signal. Backlinks and domain authority still matter, but mentions, citations, and entity authority across the open web matter more for whether the AI cites your passage.
• Output format. Classic search returned a list of links. AI search returns one synthesized answer. There is no second-place click. You either get cited or you do not.
• Measurement. Classic SEO measured rank position. Fan-out visibility is measured across a set of real shopper questions: how often your products appear, as what, and where in the answer.

Retailers who only watch rank will underestimate how visible, or invisible, they are inside AI search. The Surfer SEO finding that most AI-cited pages are outside the organic top 10 is the simplest proof that the two systems score different things.

Three actions move fan-out visibility:

1. Write for passage-level retrieval. Each section of a product or category page should answer one question on its own. The assistant retrieves passages out of context, so each one has to stand alone.
2. Complete product data so each SKU answers more sub-queries. Ingredients, certifications, use cases, dimensions, comparisons and the other details your category asks about.
3. Measure across the question space. Sample the questions your shoppers actually ask and track how often your products appear, and as what.

Treating fan-out as a content problem alone plateaus quickly. The larger gains come from the product information itself: attributes, descriptions, Q&A and schema on every product page. That is the work Paz handles. A Paz expert finds which sub-queries your products fail to answer, investigates gaps and corrects supported product information from your sources and for the shoppers you sell to, our experts check the changes against agreed guidelines, and the platform tracks appearances over time. See the AI visibility service.