SECTOR / POLICY
Simulate the election before the message goes live.
Forecast the vote. Randomize the message. Measure what changes support.
0-7 days
Typical benchmark polling fieldwork takes most of a week. The money is in learning which message changes the outcome while the election is still live.
THE DECISION
Which message changes the outcome, not just the topline?
Run election, issue, and message scenarios before airtime. Compare direction, lift, and uncertainty across the electorate.
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 ↗