Research · ChatGPT fan-outs

How does ChatGPT build its query fan-out about your brand?

When ChatGPT answers a question, the query fan-out it runs doesn’t target what you asked. It quietly rewrites your question — often into another language — and searches for that instead. Vercite analysed 17,806 ChatGPT fan-out queries from our own platform data to see exactly what it looks for.

Fan-out queries per answer
~2
per single answer
Rewritten in another language
41%
mostly into English
New words vs your prompt
64%
it reformulates
Phrased as a question
0.5%
keywords, not questions
The hidden middle step

What is a query fan-out?

It’s ChatGPT’s query fan-out: the set of background searches it runs to answer you, queries nobody typed. Your brand isn’t competing for the user’s question; it’s competing for the queries ChatGPT derives from it.

01
You ask

A user types one prompt into ChatGPT, in their own words and their own language.

02
It searches

Before answering, ChatGPT silently issues its own background search queries. That set is the query fan-out.

03
It reads

Each fan-out query pulls sources from the web. Whatever ranks for those strings becomes the raw material.

04
It answers

The reply cites the brands and pages the fan-out surfaced — not the ones that rank for your original prompt.

One prompt, the query fan-out it became
bästa löparskorna för vintern?
A user’s prompt — Swedish for “the best running shoes for winter?
ChatGPT’s fan-out, in English
best winter running shoes 2026winter running shoe grip comparisontrail vs road shoes for snowbest running shoes for ice and snow+ more
How wide it casts

How many fan-out queries does ChatGPT run per answer?

Fewer than you’d think — about two. In a single answer ChatGPT’s query fan-out is roughly two distinct queries. Ask the same question repeatedly over weeks, though, and it explores a far wider set as it keeps re-phrasing — about 38 distinct fan-out queries in total.

Fan-out queries in one answer
~2

1.9 distinct fan-out queries per response, on average.

Per single answer
1.9
Cumulative across ~25 repeat checks
38

The wide number is a vocabulary built up over time, not a single burst. ChatGPT keeps your topic but varies how it phrases the fan-out from run to run.

Same language, or not

Does ChatGPT’s query fan-out use your language?

Often not. 41% of its fan-out queries are in a different language than your prompt — and when the prompt is in a local language, that means the question is rewritten into English. To rank in the query fan-out ChatGPT actually runs, English content can matter even when your customer typed Swedish.

41%TRANSLATED
Different language than your prompt

Roughly four in ten fan-out queries are rewritten into another language before the fan-out runs.

Language of ChatGPT’s fan-out queries
English 52.4%Swedish 36%Norwegian 4.8%Finnish 1.7%Other 5.1%
Reuse or reinvent

How much does ChatGPT rewrite your prompt?

Heavily. 64% of the words in ChatGPT’s fan-out queries never appeared in your prompt. Part of that is translation — but not all: even when it keeps your language it swaps out roughly half the words, and when it translates, almost all of them.

48%
new words · same language

When the fan-out stays in your prompt’s language, about half the words are still new. It genuinely reformulates.

88%
new words · translated

When it translates, nearly every word changes — translation and reformulation compound.

How close each fan-out query stays to your prompt’s wording
16%40%44%
Near-verbatimPartly rewrittenFully reformulated

Only 16% of fan-out queries stay close to your wording. The other 84% reword it meaningfully — so exact-match optimisation to your customer’s phrasing isn’t enough. 64% new words · 30% word overlap on average.

What it’s really asking

What is ChatGPT actually asking for?

It works the whole funnel — and it likes to be taught. Location and best-of questions lead, but a striking share of fan-out queries ask ChatGPT to define, explain or guide. Share of distinct fan-outs that signal each intent; a query can carry more than one.

Location
32.7%
Best / top
21.5%
How-to
21.4%
Definition
10.2%
Buy / for sale
7.7%
Comparison
6.3%
Price / cost
5.1%
Reviews
4.6%
The words it reaches for

Which words does ChatGPT use most?

How, best and what lead — followed by a distinctive guide-and-define streak that shows ChatGPT asking to be taught the topic. The mint figure is each word’s share of all distinct fan-outs; multilingual variants are folded into one label.

how26%popular1.7%best19%choose1.8%what17%compare2.3%guide6.3%good2.8%define5.4%buy3.3%top5.4%review3.9%price4.9%
Query texture

What do ChatGPT’s fan-out queries look like?

Long, descriptive and keyword-shaped — not the question your user typed.

Avg words per fan-out query
10.3

Long, qualified phrases — not short keywords.

Phrased as a question
0.5%

Almost always a keyword string, not a natural question.

Use your exact wording
16%

The rest reword your prompt in the fan-out.

What to do with this

How do you get cited by ChatGPT?

Optimise for the query ChatGPT writes, not the one your customer types.

Publish strong English content, even for local markets. ChatGPT translates four in ten fan-out queries into English — local-only content can be invisible to it.
Cover definitional and how-to content. A large share of fan-outs ask ChatGPT to explain, define or guide — pages that teach the topic get pulled in.
Don’t rely on exact-match phrasing. 84% of fan-out queries reword the prompt, so target the concept and its variants, not one keyword.
Win the top and middle of the funnel. Location, best-of, comparison and definition dominate ChatGPT’s query fan-out.
Methodology & notes
What we measured
A query fan-out is a background search ChatGPT issues while answering. “Distinct” counts unique query strings; we deduplicate identical strings within a prompt.
Per answer vs cumulative
“~2 per answer” is the average within a single response. “~38” is the cumulative distinct set a prompt accumulates across repeated checks over the window — not queries fired in one answer.
Language
Detected algorithmically. On very short strings this is approximate; the direction (heavy translation into English) is robust, the exact percentage is indicative.
Intent & words
Tagged with multilingual keyword patterns, which lean English and can overlap, so intent shares are directional. New-word ratios compare each fan-out query’s words against its prompt.
Scope
This study covers ChatGPT only. Vercite tracks Gemini, Perplexity and Google AI separately; engine behaviour changes over time, so figures are a snapshot of this window.
‹ Vercite ›ChatGPT fan-out studyVercite platform data17,806 fan-out queriesPublished · June 2026Stockholm · Sweden

Try Vercite for free today

Monitor your brand across ChatGPT, Gemini, Perplexity & Google AI

Get started free