Ni — The Nuance Index
The Nuance Collective  ·  2026

The Nuance Index™

How clearly do AI assistants understand a category? Every Friday we measure one — whether the answers it gives are settled, accurate, and anchored to the real market. One locked method, all year.

How to read it →
Rationale

What it measures

01

The subject is the category

The Index asks whether AI assistants give a coherent account of a whole category — settled, accurate, and anchored to the real market. One category a week, the same instrument every time.

02

Clarity, measured three ways

Whether it answers the same way twice, whether what it says is true, and whether its ranking matches the real category. Those three roll into one number from 0 to 100, and a word for which kind of clarity it is.

03

Brand positions are the evidence

Where each brand lands is how we read the category. How clear the category is then decides whether that position can be moved, which is why the verdict matters more than the row.

The method in plain English →
Editions

Published

Fifty-three symbols, one a week. The symbol belongs to the category, not to us — assigned when the category is scheduled, unique across the season, unchanged if we run it again.

004HdHot Dogs
Edition 004  ·  21 August 2026

Hot Dogs

81.6 Clear

A hundred and twenty years after Upton Sinclair published The Jungle, the cliche about asking what's in a hotdog is still the same: “you don't wanna know.” A fifth of the frankfurter labels filed with the federal government don't name a specific meat. That isn't an omission, it's an admission: a pack that just says “Franks” is legally disclosing it's a melange of meats. But what we didn't expect is that the AI answering our shopping questions has absorbed the manners of the category it describes: where it knows, it is precise, but where it doesn't, it just keeps talking.

Read the edition →
003LgLuggage
Edition 003  ·  14 August 2026

Luggage

63.6 Blurry

Nearly every answer said the same thing: the bag dies at the wheels, the handle or the zipper, so the only question worth asking is who pays. That makes warranty fine print the deciding factor in this category — and the fine print is exactly where the answers are least current.

Read the edition →
002WdWomen's Deodorant
Edition 002  ·  7 August 2026

Women's Deodorant

65.1 Unsettled

Arrid: 0 of all 50 runs, both nouns — and not for want of knowledge. Asked directly, the model puts Arrid in this category 3 of 3 times and recites its history down to the ad slogans. Known, accepted, never recommended.

Read the edition →
001RbRegional Banks
Edition 001  ·  31 July 2026

US Regional Banks

62.3 Unsettled

TD Bank: 0 of all 50 runs, both nouns — and not for want of knowledge. Asked directly, the model puts TD in this category 3 of 3 times and returns 15 specific facts about it. Known, accepted, never recommended.

Read the edition →
49 categories still to run this season.
Every Friday
How to read it

Four things worth knowing

It scores a category
The number describes the category's clarity. Where a brand lands is evidence of that, which is why the same position means different things in a settled category and an unsettled one.
Not a visibility metric
Share-of-voice tools count how often a brand appears. Clarity asks whether the picture it is appearing inside makes sense at all. A brand can be highly visible in a category the model gets wrong, and no visibility number can tell that apart from a good position.
Known ingredients
We publish the dimensions, the component scores, the reference set, the run count and the exact category nouns. We never publish the weighting or the prompt wording.
Bands, not places
Twenty-five runs are a sample. Every figure carries the range it moves inside when those runs are resampled, and brands are grouped into bands cut where the ranges stop overlapping. Inside a band, the data does not separate them.
A stated inclusion rule
Each edition publishes what qualified an entity to be measured — entity type, size band, classifying authority, as-of date, source linked. The thresholds are ours and labelled as ours; the entity list and the figures are not.
Comparable only to itself
A 62 in snack crackers does not mean what a 62 in another category means. Each edition stands alone, and no edition cites another's score.
The full guide — two minutes →