# Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation > Source: > Published: 2026-09-22 13:00:01+00:00 Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents. Exhaustive testing is expensive, so evaluation rests on a sample of labeled units. We treat the evaluation set as a finite population