Q91 — AWS AIF-C01 Ch.1

Question 91 of 100 | ← Chapter 1

A company needs to select a model from Amazon Bedrock for internal use. The company must ensure that the model generates responses whose style aligns with employee preferences. What should the company do to meet these requirements?

• A. Evaluate the models using built-in prompt datasets.
• B. Evaluate the models using human reviewers and custom prompt datasets. ✓
• C. Identify models using public model leaderboards.
• D. Use the ModelInvocationLatency runtime metric in Amazon CloudWatch when testing models.

Correct Answer: B. Evaluate the models using human reviewers and custom prompt datasets.

Explanation

To select a model from Amazon Bedrock that satisfies employee preferences for response style, the company must adopt targeted evaluation methods. Using human reviewers and custom prompt datasets ensures that generated responses match employee stylistic preferences. This approach allows the company to tailor evaluation criteria to specific employee needs and preferences, enabling selection of the most suitable model. Other options—such as using built-in prompt datasets, public model leaderboards, or solely relying on InvocationLatency metrics—do not adequately address alignment between model output style and employee preferences.