[VELIU· LUCE](https://luce.veliu.com/index.html)
how AI engines recommend brands
PILOT · W30 Search / (Search brands, categories and engines)
Board ▾
Board [Overview](https://luce.veliu.com/index.html) [Running shoes](https://luce.veliu.com/c/running-shoes.html) [Wireless earbuds](https://luce.veliu.com/c/wireless-earbuds.html)
[Coffee machines](https://luce.veliu.com/answers.html#coffee-machines) measuring
[Robot vacuums](https://luce.veliu.com/answers.html#robot-vacuums) measuring
[Air fryers](https://luce.veliu.com/answers.html#air-fryers) measuring
[All brands](https://luce.veliu.com/brands.html) [Real answers](https://luce.veliu.com/answers.html)
Engines [ChatGPT](https://luce.veliu.com/e/chatgpt-web.html) [ChatGPT API](https://luce.veliu.com/e/chatgpt-api.html) [Gemini](https://luce.veliu.com/e/gemini.html) [Perplexity](https://luce.veliu.com/e/perplexity.html)
Research [Coverage](https://luce.veliu.com/coverage.html) [Methodology](https://luce.veliu.com/methodology.html) [Sources](https://luce.veliu.com/sources.html) [Glossary](https://luce.veliu.com/glossary.html) [Tools](https://luce.veliu.com/tools) (primary)
en-US · grammar luce-live-v0 Dark (Current theme: dark) (wave luce-live-w30 · grammar luce-live-v0 · generated 2026-07-15 19:49:02 UTC)
**PILOT · W30** real engine answers · small pilot wave · wide intervals by design Synthetic probes · not real user sessions · this wave 100% [L3](https://luce.veliu.com/glossary.html#provenance-tier) · answers [L1](https://luce.veliu.com/glossary.html#provenance-tier) elicited
All categories▾
[All categories](https://luce.veliu.com/index.html) [Running shoes](https://luce.veliu.com/c/running-shoes.html) [Wireless earbuds](https://luce.veliu.com/c/wireless-earbuds.html)
·
All engines▾
[All engines](https://luce.veliu.com/index.html) [ChatGPT](https://luce.veliu.com/e/chatgpt-web.html) [ChatGPT API](https://luce.veliu.com/e/chatgpt-api.html) [Gemini](https://luce.veliu.com/e/gemini.html) [Perplexity](https://luce.veliu.com/e/perplexity.html)
· en-US · LUCE-LIVE-W30 · measured from 15 Jul 2026 · 61 days ago (what you are viewing)
how to read Luce
# Every term on the board, in plain words.
Luce measures how often AI engines recommend brands. It shows ranges with their uncertainty, publishes only real measurements, and never collapses an engine's answer into a single winner. These are the words it uses.
Mention rate
How often a brand is named in answers to Luce’s published question set, with uncertainty estimated across prompt clusters.
95% confidence interval
The range the true mention rate very likely sits in, given the sample. A wide interval means fewer samples, so Luce publishes a range. When two brands' intervals overlap, the data cannot separate them.
League
A band of brands the data cannot rank apart. Brands in one league share a shelf. Luce publishes the band and never prints a single position, because an engine's answer varies from one ask to the next.
Rank range
The span of positions a brand plausibly holds. Luce never collapses it to one rank. Overlapping ranges read as a tie.
Measuring
A category awaiting board publication or an estimate still gathering observations toward its precision gate.
Provenance tier
How real a measurement is. L0 is observed in the wild, L1 is a real answer Luce elicited with its own prompt, and the lower tiers are derived or synthetic. Only the real tiers are published, and they are never pooled with synthetic ones.
Measured surface
Where a number was observed. The consumer interface (the ChatGPT web app a shopper uses) and the developer API can recommend different brands, so every number states its surface.
Wave
One dated round of measurement. A trend needs several waves before Luce shows a significance arrow.
Divergence
How much brands’ measured mention patterns or top-league membership differ across surfaces or engines, reported with a confidence interval.
Effective sources
How many publishers a set of citations really behaves like, once concentration is taken into account. Ten citations spread evenly over five sites count as five; ten citations where one site takes nine count as close to one. It is the inverse-Herfindahl number of the cited domains, and it counts diversity, so it carries no confidence interval.
Prompt cluster
One question from the Luce grammar together with every repetition of it. The n on a cell counts prompt clusters, and the confidence interval comes from a bootstrap over them, because five repetitions of the same question yield one independent fact.
The full method, the estimand, and the provenance ladder are on the [methodology page](https://luce.veliu.com/methodology.html) .
Published by Veliu Research Lab. Veliu sells services to brands measured here.
Live pilot wave luce-live-w30. The method, the probe log and this wave's coverage are on the methodology page.