Q56 — AWS AIF-C01 Ch.2

Question 56 of 100 | ← Chapter 2

How can a company securely use large language models (LLMs) on Amazon Bedrock?

• A. Design clear and specific prompts. Configure AWS Identity and Access Management (IAM) roles and policies with least-privilege access. ✓
• B. Enable AWS Audit Manager to automate model evaluation jobs.
• C. Enable Amazon Bedrock automated model evaluation jobs.
• D. Use Amazon CloudWatch Logs to improve model interpretability and monitor for bias.

Correct Answer: A. Design clear and specific prompts. Configure AWS Identity and Access Management (IAM) roles and policies with least-privilege access.

Explanation

Securely using LLMs on Amazon Bedrock hinges on robust access control and permission management. Designing clear and specific prompts improves task understanding and execution, while configuring IAM roles and policies with least-privilege access restricts resource permissions to only those necessary for required tasks—significantly reducing security risks. While other options address monitoring, auditing, or model evaluation, they do not directly address core security concerns related to access control and permissions.