Preparing Practice Exam…
Please wait a moment while the system generates the exam questions, answers, and study session.
Please wait a moment while the system generates the exam questions, answers, and study session.
AWS Certified AI Practitioner · AWS
Select one answer.
Written by other learners. Comments can disagree with the marked answer — check the official documentation when in doubt.
Guardrails for Amazon Bedrock is purpose-built for this: - Sensitive information filters can detect and block PII (names, SSNs, medical record numbers, etc.) from model responses - Guardrails integrates natively with Amazon Bedrock models - Violations are logged as CloudWatch metrics, enabling alarms and notifications when policies are triggered
A. Use Amazon Macie to scan the model's output for sensitive data and set up alerts for potential violations. Amazon Macie is an AI service that detects breaches of private information (PII). On the other hand, Guardrails for Amazon Bedrock is a service used to guard against hallucinations in generative AI apps. Amazon Macie is much more appropriate if you want to filter out private content.
Incorrect analysis. Read the question again, it clearly says that the company wants to "prevent" the model from displaying any personal patient information. Means, the company is looking for some preemptive measures/solutions in place to detect and filter out such sensitive information proactively. Including a method to notify alerts upon detection via CloudWatch alarms. That's why option C is a great fit for this question's requirments.