SECTOR / CPG
Know what deserves shelf space before you fund the launch.
Test product, price, pack, and claim before launch capital moves.
66%
Of shoppers enter the store with a brand already in mind. The money is in knowing which price, pack, and claim makes them switch, buy, and buy again.
Illustrative comparison, not a customer result
Which vanilla ice cream pack should reach the shelf test?
A category team compares pack and price alternatives for shoppers choosing vanilla ice cream. Flavor and the underlying product stay fixed; pack size, shelf price, nutrition information, and organic claims are the attributes to compare.
Single-occasion pack
A smaller pack positioned for one occasion. Compare its shelf price and claim presentation with the larger alternative.
Family pack
A larger pack positioned for repeated occasions. Compare the same nutrition and claim information alongside pack size and shelf price.
Response compared
Compare modeled product choices between the two packs and neither, at the pack-and-price combinations in the study. Product preference does not establish repeat purchase or total category demand.
Decision interpretation
A sample decision brief would identify a pack-and-price combination for the next shopper test and show the margin trade-off. A preferred option is a test candidate, not an observed sales winner.
Next validation
Confirm choices with human shoppers and a shelf or retailer test. Check pack execution, unit economics, and repeat behavior before funding a launch.
A LIVE CATEGORY TEST
THE DECISION
Which product earns the shelf, protects margin, and gets bought again?
Walk into the retailer meeting with a ranked slate: what to launch, where to price it, which pack to show, which claim to lead with, and what each move does to category value.
VALIDATED WEEKLY
0.73
Mean rank agreement
43 design-filtered human studies
Confidence, with every report.
Every report carries graded confidence. Each week, we test the system against held-out human data and publish the full benchmark, including mid-range results and failures.
Read the validation paper ↗