AWS Certified Generative AI – Professional (AIP-C01) — Question 35

A medical company uses Amazon Bedrock to power a clinical documentation summarization system. The system produces inconsistent summaries when handling complex clinical documents. The system performed well on simple clinical documents.
The company needs a solution that diagnoses inconsistencies, compares prompt performance against established metrics, and maintains historical records of prompt versions.
Which solution will meet these requirements?

Answer options

• A. Create multiple prompt variants by using Prompt management in Amazon Bedrock. Manually test the prompts with simple clinical documents. Deploy the highest performing version by using the Amazon Bedrock console.
• B. Implement version control for prompts in a code repository with a test suite that contains complex clinical documents and quantifiable evaluation metrics. Use an automated testing framework to compare prompt versions and document performance patterns.
• C. Deploy each new prompt version to separate Amazon Bedrock API endpoints. Split production traffic between the endpoints. Configure Amazon CloudWatch to capture response metrics and user feedback for automatic version selection.
• D. Create a custom prompt evaluation flow in Amazon Bedrock Flows that applies the same clinical document inputs to different prompt variants. Use Amazon Comprehend Medical to analyze and score the factual accuracy of each version.

Correct answer: B

Explanation

Option B is correct because it involves version control and a testing framework that accommodates complex clinical documents, allowing for effective comparison and historical tracking. Option A lacks automation in testing and relies on manual efforts. Option C focuses on endpoint traffic distribution rather than comprehensive evaluation and tracking of prompt performance. Option D, while utilizing Amazon Comprehend Medical, does not provide a structured approach to version control and performance comparison.