AWS Certified Generative AI – Professional (AIP-C01) — Question 16

A company is building a generative AI (GenAI) application that produces content based on a variety of internal and external data sources. The company wants to ensure that the generated output is fully traceable. The application must support data source registration and enable metadata tagging to attribute content to its original source. The application must also maintain audit logs of data access and usage throughout the pipeline.
Which solution will meet these requirements?

Answer options

• A. Use AWS Lake Formation to catalog data sources and control access. Apply metadata tags directly in Amazon S3. Use AWS CloudTrail to monitor API activity.
• B. Use AWS Glue Data Catalog to register and tag data sources. Use Amazon CloudWatch Logs to monitor access patterns and application behavior.
• C. Store data in Amazon S3 and use object tagging for attribution. Use AWS Glue Data Catalog to manage schema information. Use AWS CloudTrail to log access to S3 buckets.
• D. Use AWS Glue Data Catalog to register all data sources. Apply metadata tags to attribute data sources. Use AWS CloudTrail to log access and activity across services.

Correct answer: D

Explanation

Option D is correct because it specifically addresses the need for data source registration, metadata tagging, and maintaining audit logs through AWS CloudTrail. Option A, while it suggests cataloging and monitoring, does not focus on data source registration and tagging as effectively. Option B lacks the comprehensive logging aspect and does not utilize AWS CloudTrail for tracking. Option C misses the explicit mention of metadata tagging for attribution, which is key in this scenario.