How we measure.
Neutral shopping queries, replayed once a week with 4 runs per AI, judged against your catalog.
8AIS
4RUNS PER AI
95% CICONFIDENCE INTERVAL
WebSEARCH ON
Neutral queriesEach AI × 4 runsExtractionJudgment vs catalogReport
Each AI is queried in the market's language and currency.
Four principles.
01
We sample, we don't measure once.
Each query is replayed 4 times on each AI. Figures are shown with their 95% confidence interval.
02
Queries are neutral and never name your brand.
We ask what a shopper would ask: a category, a budget, a use.
03
Web search is on.
To read today's catalog, not the model's memory.
04
Every answer is judged against your catalog and listings.
Price, stock, features: accurate, missing, distorted or wrong.
AI Shelf ReportW36 · 800 answers · France · 95% CI
VISIBILITY
0%
+4.2 pts
PERCEPTION
0
/100
ACCURACY
0%
2 critical
Correlation, not causation.