How does query fan-out work?
Query fan-out works in three steps. The AI model reads the question, writes a set of related searches that together would answer it, and runs them at the same time against the search index. It then picks the best passages from all the results and writes one answer.
Google gives this example in its 2026 guide. The question "how to fix a lawn that's full of weeds" fans out to searches such as:
- best herbicides for lawns
- remove weeds without chemicals
- how to prevent weeds in lawn
Each sub-search retrieves its own pages. The final answer can cite a different source for each part. Google notes that fan-out is one reason AI Overviews and AI Mode show a wider range of links than a classic results page.
Why does query fan-out matter for AEO?
Fan-out changes which pages get retrieved. A page that ranks for the main question but ignores the follow-ups competes for one slot. A page that answers the follow-ups clearly competes for several. Each sub-search is a new chance to be the cited source.
It also rewards depth over volume. One page that covers a topic and its natural follow-ups beats ten thin pages, each chasing one variation.
How do you find the fan-out queries for a topic?
You find them by collecting the questions an AI model would ask on your reader's behalf. Five sources work well:
- QueryFanOuts. QueryFanOuts, built by aeo.so's author, generates the follow-up queries AI search is likely to run for a topic.
- People Also Ask. Google's question boxes show related questions real searchers ask.
- AI answers themselves. Ask ChatGPT, Perplexity and Google your question and note the headings and sub-topics their answers cover.
- AI Overview follow-ups. Google's AI answers often end with suggested next questions.
- Keyword data. Question-form keywords that contain your topic, with search volumes.
A worked example: "what is AEO"
aeo.so planned its guide to answer engine optimization this way. The question "what is AEO?" fans out to questions such as:
| Fan-out question | Where it showed up |
|---|---|
| What does AEO stand for? | People Also Ask |
| How does answer engine optimization work? | ChatGPT's answer structure |
| What is the difference between AEO and SEO? | People Also Ask, 1,900 searches a month |
| What is the difference between AEO and GEO? | Google AI Overview follow-up |
| What is an example of AEO? | People Also Ask |
| How do you measure AEO? | ChatGPT's answer structure |
| Do I need llms.txt for AEO? | ChatGPT's answer structure |
Each became a heading with its own short answer on one page. The bigger ones, such as AEO vs SEO, also got their own guide, linked from that heading.
How do you write for query fan-out?
Write one page per topic, with one section per follow-up question:
- Use the question as the heading, in the words people use.
- Answer it in the first 40 to 60 words under the heading, in a passage that makes sense on its own.
- Then go deeper with steps, examples, a table or data.
- Link to a separate guide when a follow-up needs more than a few paragraphs.
- Check coverage by running your draft against the fan-out list before you publish.
The checklist tactic create content that addresses implied and related queries puts this into practice.