Exam-style
A review board asks how the team will detect whether their assistant gives noticeably weaker answers to some customer groups than others, and whether it repeats stereotypes about them. Which responsible-AI dimension is that, and which control carries it?
Reveal the answer
D. Fairness, carried by SageMaker Clarify bias metrics and prompt-stereotyping evaluation
Quality disparity between groups and stereotyped output are the fairness dimension, and Clarify’s bias metrics and foundation-model stereotyping evaluation are the controls that measure them. The other dimensions each own a different concern: safety is about harmful content, controllability is about steering and human oversight, veracity is about grounding answers in something true, and transparency is about disclosing how the system works. Mapping the concern to the right dimension is what picks the right tool.
Q. AWS names its responsible-AI dimensions. Roughly, what are they?
A. Fairness, explainability, privacy and security, safety, controllability, veracity and robustness, governance, and transparency. Each maps to concrete controls:
| Dimension | Controls that carry it |
|---|---|
| Fairness | SageMaker Clarify bias metrics, before and after training |
| Explainability | Clarify feature attributions; SageMaker Model Cards for the record |
| Privacy and security | Guardrails PII filters and anonymisation; IAM, KMS, PrivateLink around the data path |
| Safety | Bedrock Guardrails content filters and denied topics |
| Controllability | Human review via Amazon A2I; monitoring and feedback loops to steer behaviour |
| Veracity and robustness | Contextual grounding checks, Knowledge Base citations, model evaluation jobs |
| Governance | SageMaker Role Manager, Model Cards, Model Dashboard; invocation logging and CloudTrail for audit |
| Transparency | AWS AI Service Cards; Model Cards and visible citations in your own app |
Why? The point is to map a concern to the right dimension and tool, not to hand-wave being responsible.