Tool that detects potential bias in training data and in ML model predictions, and generates explanations for predictions (feature importance) to improve model transparency.
In AIF-C01 (Domain 4) it's the specific service for responsible AI at the bias-detection level. It's complemented by SageMaker Model Monitor (detects drift in production) and Amazon A2I (Augmented AI, human review of low-confidence predictions).
Amazon SageMaker Clarify is a concept that can show up on the exam. Check the full guide to see it in context.