Amazon SageMaker Clarify

Evaluate models and explain model predictions

Benefits of SageMaker Clarify

Automatically evaluate FMs for your generative AI use case with metrics such as accuracy, robustness, and toxicity to support your responsible AI initiative. For criteria or nuanced content that requires sophisticated human judgment, you can choose to leverage your own workforce or use a managed workforce provided by AWS to review model responses.
Explain how input features contribute to your model predictions during model development and inference. Evaluate your FM during customization using the automatic and human-based evaluations.
Generate easy to understand metrics, reports, and examples throughout the FM customization and MLOps workflow.
Detect potential bias and other risks, as prescribed by guidelines such as ISO 42001, during data preparation, model customization, and in your deployed models.

Evaluate foundation models (preview)

  • Evaluation wizard and reports