Features / Measure / Fan-outs

Only the fan-outs AI
actually discloses.

Google Gemini, Claude and ChatGPT reveal the background searches they ran to answer a prompt. Perplexity gives a count. Google AI Overviews discloses nothing. llemmy shows you exactly which is which, and never fills the gap with a guess.

No credit card · Every query is real · Nothing reconstructed
Fan-outs
Background searches disclosed for Northwind Coffee · refreshed daily
What each engine actually discloses
Gemini
Real · disclosed
Claude
Real · disclosed
ChatGPT
Real · disclosed
Perplexity
Count only
AI Overviews
Not exposed
Distinct queries, by frequency
Disclosed queryFreqBrands named
top-rated pour-over coffee gear18Northwind, Aurora, PeaklineTrack rank
best coffee subscription service14Aurora, Harbor RoastingTrack rank
ethically sourced coffee beans11Northwind CoffeeTrack rank
specialty coffee roasters near me9Peakline, Harbor RoastingTrack rank
Northwind Coffee named inside 34% of disclosed queries · n=64 · 95% CI 24–46%

A smaller, honest number beats a padded one.

Before an AI engine answers, some of them search first. Those background queries are a rare, direct look at how an engine actually researches your category, when the engine is willing to show its work.

3 of 5
Engines that actually disclose

Gemini, Claude and ChatGPT hand back the real background queries. The other two get an honest label instead of a guess.

0
Invented queries

Every query you see is one an engine actually ran and disclosed. If it isn't real, we don't show it.

Daily
Refreshed automatically

Fan-outs are captured on every scheduled run, so the query mix stays current as your prompts do.

Honest, by construction

The smaller number is the honest one.

Some tools show a single fan-out count that blends real, provider-disclosed queries with ones reconstructed or inferred from the answer text. llemmy doesn't blend. We show only what an engine actually hands back, and we label the rest plainly instead of guessing.

RealGemini, Claude and ChatGPT return the actual background queries they ran, verbatim
Count onlyPerplexity discloses how many searches it ran, not what they were
Not exposedGoogle AI Overviews doesn't disclose fan-out queries at all, so we say so instead of inventing them
Coverage, by engine
GeminiFull background query list, provider-disclosedReal
ClaudeFull background query list, provider-disclosedReal
ChatGPTFull background query list, provider-disclosedReal
PerplexitySearch count only, no query text disclosedCount only
AI OverviewsNothing disclosed on fan-out queriesNot exposed
Ollama is a self-hosted utility model and isn't included in fan-out coverage.
See who else showed up

See which brands compete inside the AI's own research.

Every disclosed query gets scanned for brand mentions, yours and your rivals'. See how often a brand appears inside the background searches themselves, not just the final answer, with the sample size and confidence interval behind the number.

Named in the fan-out: how often your brand appears inside the disclosed queries, not just the visible answer
One-click Track rank: add any disclosed query straight into your tracked prompt list
Sample size and 95% CI on every proportion, so a handful of queries never masquerades as a trend
Named inside disclosed queries · 30 days
Northwind Coffee You34%
Aurora Roasters41%
Peakline Coffee23%
Based on 64 provider-disclosed queries across Gemini, Claude and ChatGPT · 95% CI 24–46% for Northwind Coffee
The honest promise

Fan-outs are not a vanity count. We show exactly what an AI engine discloses and label the rest instead of inventing it: real and provider-disclosed, count-only, or not exposed. Brand-in-fan-out proportions carry their sample size and a 95% confidence interval. Measured over the official model APIs and Google AI Overviews read off the SERP, not the logged-in apps; personalization isn't modeled. Full limits in our methodology.

Keep exploring
AI visibility
Track how often AI names you →

The mention rate, with confidence intervals, that a tracked fan-out feeds.

Competitor intelligence
See who AI recommends first →

Share of voice and threat tracking across every rival, on every engine.

← Back to all features
From the resource library Query fan-out: the searches an AI runs before it answers → How llemmy measures AI visibility →

See your real fan-outs free.

First insights in under five minutes. No credit card. Every query we show you is one an engine actually disclosed.

Start free → Talk to our team