AWS Certified AI Practitioner (AIF-C01) — Question 33

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

Answer options

• A. Design clear and specific prompts. Configure AWS Identity and Access Management (IAM) roles and policies by using least privilege access.
• B. Enable AWS Audit Manager for automatic model evaluation jobs.
• C. Enable Amazon Bedrock automatic model evaluation jobs.
• D. Use Amazon CloudWatch Logs to make models explainable and to monitor for bias.

Correct answer: A

Explanation

The correct answer, A, emphasizes the importance of crafting specific prompts and implementing least privilege access through IAM roles, which is crucial for security. Options B and C focus on model evaluation but do not address secure access management. Option D pertains to monitoring bias and explainability, which, while important, does not directly relate to securely using LLMs.