Research study
The Say-Do Gap: Predicting What People Do, Not Just What They Say
We tested four ways to predict consumer behaviour against what actually happened. One matched reality on its home turf — and the honest version, including where it ties or loses, is more useful than…
- Who was asked
- US adult clones with a real-world behaviour benchmark, 235 clones
- When
- June 2026
- How
- Predicted responses from Brox clones, each built from a long-form interview with a real person, run on the Brox platform.
The full report The Say-Do Gap: Predicting What People Do, Not Just What They Say Open the report
Section 01: What the study found
Section 02: Where this sits
Ask this of your own customers: humans@brox.ai
More in Research methods
All in Research methods-
The room emptied. The pillars stayed.
2.5pp clone error against real behaviour, in percentage points (base 235)
Read -
Mad vs. Annoyed — A Cross-Cultural Pragmatic Analysis
870 matched US and UK clones answered 15 identical scenarios (base 870)
Read -
Clones Don't Lie to Look Good: Testing for Social-Desirability Bias
0.07 the widest say-do gap found across five socially loaded items (1-5 scale) (base 546)
Read