AWS Certified AI Practitioner (AIF-C01) — Question 284

A financial services company must ensure that its generative AI-powered chatbot provides factual responses for regulatory compliance.

Which solution prevents the underlying foundation model (FM) from hallucinating?

Answer options

• A. Use AWS Config to query compliance metadata by using natural language.
• B. Configure Amazon Bedrock Guardrails to evaluate user inputs and model responses.
• C. Use Amazon Fraud Detector to detect potentially fraudulent online activities.
• D. Use AWS Audit Manager to prepare IT audit and compliance reports.

Correct answer: B

Explanation

Amazon Bedrock Guardrails helps prevent foundation model hallucinations by evaluating and filtering user prompts and model responses against predefined safety and accuracy boundaries. In contrast, AWS Config, Amazon Fraud Detector, and AWS Audit Manager serve different purposes like resource tracking, fraud identification, and compliance reporting, and cannot directly mitigate generative AI hallucinations.