applied ai June 24, 2026 4 min read
Scoring people fairly: the explainability burden of rating humans with AI
Composite scores that rank people — blending grades, social signals, and demonstrated skill — are some of the highest-stakes models you can ship. The hard part isn't the math; it's earning the right to be trusted with a number that changes someone's life.
When AI assigns a single score to a person, explainability and bias aren't features — they're the whole product. Here's how to build composite rating systems that hold up.
Keith Pattison
Founder, Black Flag Design