Q69 — AWS AIF-C01 Ch.1

Question 69 of 100 | ← Chapter 1

How can enterprises 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. ✓
• B. Enable AWS Audit Manager for automated model evaluation workflows.
• C. Enable Amazon Bedrock automated model evaluation jobs.
• D. Use Amazon CloudWatch Logs to make models interpretable and monitor bias.

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

Explanation

This question tests secure usage practices for large language models on Amazon Bedrock. Secure usage requires well-crafted prompts and appropriate permission controls. Option A addresses both prompt engineering and IAM role/policy configuration—key measures for security. Options B (Audit Manager), C (automated evaluation), and D (CloudWatch for interpretability and bias monitoring) are not direct security controls for LLM usage. Thus, option A is correct.