Underwriting, with the error bar attached
A score without an error bar is an opinion.
Every number here is drawn inside the interval we measured by re-running the same input ten times. We publish the misses too.
55
± 3.1
PROVE
REWORK
PROVE
BUILD
rubric w3.0-20260804 · interval ±3.1 at 95% (n=10, sd=1.6, measured 2026-08-04) · the band is what re-running the same input actually produces
That band is not a design flourish. It is what happened when the same candidate was run through the same rubric ten times: 53 at the low end, 57 at the high end, standard deviation 1.6. It cost $4.76 to find out. A score that straddles a gate is not a verdict, and this is the only way to see that.
Four questions, four rubrics
Operate
Should I run this licensed business?
Buy
Should I acquire this business?
Build
Should I create this?
Take over
Should I take this over?