AWS Certified AI Practitioner (AIF-C01) — Question 177

A company is creating an agent for its application by using Amazon Bedrock Agents. The agent is performing well, but the company wants to improve the agent’s accuracy by providing some specific examples.

Which solution meets these requirements?

Answer options

• A. Modify the advanced prompts for the agent to include the examples.
• B. Create a guardrail for the agent that includes the examples.
• C. Use Amazon SageMaker Ground Truth to label the examples.
• D. Run a script in AWS Lambda that adds the examples to the training dataset.

Correct answer: A

Explanation

The correct answer is A because modifying the advanced prompts allows the agent to learn from the specific examples provided, directly influencing its performance. Options B and C do not directly enhance the agent’s learning process, as guardrails and labeling are more about constraints and data preparation rather than improving accuracy through example integration. Option D involves altering the training dataset, which is useful but not as immediate as adjusting the prompts for the agent's functioning.