Keyword research tools are built to measure what humans search for. An AirOps analysis of 548,534 retrieved pages found 95% of the queries ChatGPT actually generates while composing an answer have zero traditional search volume. If you are optimising for primary keywords alone, you are covering at most two-thirds of the AI citation surface. This post covers what fan-out query coverage means and why single-keyword optimisation can actively work against you.
ChatGPT rewrites every prompt into 25+ queries before it retrieves anything
ChatGPT processes a user prompt by expanding it into sub-queries before retrieving any content. It generates 25+ unique query variations from a single prompt. Citations then come from pages ranking for these expanded queries, not just the original one the user typed.
The effect on citation surface is large. The AirOps analysis found 32.9% of cited pages were discoverable only through fan-out sub-queries, invisible through the original prompt and invisible through traditional keyword monitoring.
95% of those sub-queries had zero traditional search volume. Keyword tools do not fail because they are broken. They measure what humans search. They were never built to measure what an AI system queries internally while assembling an answer.
Covering one adjacent fan-out query more than doubles your citation rate
AirOps compared pages by their fan-out query ranking profile. Pages ranking for both the main query and at least one fan-out query achieved a 51% AI Overview citation rate, versus 20% for pages ranking only for the main query. More than a 2x lift from covering a single adjacent subtopic.
So what happens when a page tries to cover every possible sub-query?
| Fan-out coverage profile | AI Overview citation rate |
|---|---|
| Main query only | 20% |
| Main query + 1 fan-out query | 51% |
| 26-50% of fan-out sub-queries | 38.2% |
| 100% of fan-out sub-queries | 34% |
Source: AirOps, analysis of ChatGPT fan-out query coverage and citation rates.
Partial coverage beats exhaustive coverage
This is the counterintuitive finding. Pages covering 26-50% of ChatGPT's fan-out sub-queries were cited at 38.2%. Pages covering 100% of them dropped to 34%.
Focused coverage of the right subtopics beats exhaustive coverage of every subtopic. The practical read: identify the highest-value adjacent queries and build for those specifically, rather than treating fan-out coverage as a checklist to exhaust.
Single-keyword optimisation actively harms adjacent queries
Here is the part that runs against standard SEO practice. Optimising a page purely for one target query induces what AirOps calls gain allocation skew: the target query improves at the expense of related queries. Cross-query citations fall as a page gets more tightly tuned to a single keyword.
Pages optimised for a single keyword are effectively penalised in AI retrieval for the adjacent queries their topic logically covers. A hub-and-spoke content structure addresses the primary query and the fan-out queries it generates without that trade-off, because no single page is forced to carry every adjacent subtopic alone.
Retrieval is not citation: 85% of retrieved pages get discarded
Fan-out coverage gets you into the retrieval pool. It does not guarantee citation. ChatGPT retrieves roughly 6 to 7 pages for every 1 that appears in a final answer, meaning 85% of retrieved pages are discarded at the next stage.
Getting from retrieval to citation requires structural answer-extraction patterns: direct answers early in the page, title-query alignment, and clean readability. An Ahrefs analysis of 1.4 million ChatGPT prompts found 88% of citations originate from live search retrieval, not training data: the pages getting cited are pages ranking in traditional search for the specific fan-out query, then clearing content quality filters on top of that.
Fan-out behaviour is platform-specific
Google AI Mode cites only 12% of top-10 organic results, versus 38% for Google AI Overviews. Despite 86% semantic answer overlap between the two, they share only 13.7% of cited URLs. Sites outside the top 10 can still earn AI Mode citations through fan-out coverage on adjacent subtopics the top-ranked page does not address.
ChatGPT referral reach peaked at 260,000 unique domains monthly in October 2025, then contracted to 170,000 by February 2026 per Semrush, but queries per session rose from 1.21 to 1.75: 50% more fan-out opportunities per conversation. Brands with comprehensive subtopic coverage are better positioned as multi-turn conversations become more common.
What to build
Map the sub-queries AI systems generate for your primary topics by prompting an AI system directly with something like "generate 20 sub-queries an AI would generate when answering about [your topic]". Audit which sub-queries your existing content already covers, then build focused pages for the highest-value gaps rather than attempting to cover every possible variation. Structure content in a hub-and-spoke architecture so no single page bears the gain-allocation cost of single-keyword optimisation.
The bottom line
The AirOps data is observational: it shows what fan-out coverage looks like on pages that already get cited, not a controlled experiment proving that adding coverage causes citations to rise. The finding that partial coverage beats full coverage may partly reflect selection effects, pages that focus deliberately on specific subtopics may simply be higher quality overall.
The practical action holds regardless. If your keyword research stops at primary terms, you are planning for a fraction of what AI systems actually query. Map the fan-out queries, build focused coverage for the highest-value gaps, and stop tuning individual pages so tightly to one keyword that adjacent citations fall.