AIP-C01 · Question #6
A financial services company needs to pre-process unstructured data such as customer transcripts, financial reports, and documentation. The company stores the unstructured data in Amazon S3 to…
The correct answer is B. Set up an AWS Glue crawler to catalog data sources. Create AWS Glue ETL jobs to run custom. Option B is the most appropriate solution because it uses AWS-native, purpose-built data engineering and governance services to address data quality validation, metadata creation, monitoring, and transformation with minimal custom development. AWS Glue is designed specifically…
Question
A financial services company needs to pre-process unstructured data such as customer transcripts, financial reports, and documentation. The company stores the unstructured data in Amazon S3 to support an Amazon Bedrock application. The company must validate data quality, create auditable metadata, monitor data metrics, and customize text chunking to optimize foundation model (FM) performance. Which solution will meet these requirements with the LEAST development effort?
Options
- AUse Amazon SageMaker Data Wrangler to create a data flow. Configure Amazon CloudWatch
- BSet up an AWS Glue crawler to catalog data sources. Create AWS Glue ETL jobs to run custom
- CUse Amazon Comprehend to extract entities. Create an AWS Lambda function to chunk text. Run
- DCreate an AWS Step Functions workflow to orchestrate data pre-processing tasks. Run custom
How the community answered
(32 responses)- A3% (1)
- B84% (27)
- C9% (3)
- D3% (1)
Explanation
Option B is the most appropriate solution because it uses AWS-native, purpose-built data engineering and governance services to address data quality validation, metadata creation, monitoring, and transformation with minimal custom development. AWS Glue is designed specifically for large-scale data preparation and integrates seamlessly with Amazon S3, making it ideal for preprocessing unstructured datasets for downstream GenAI applications. AWS Glue crawlers automatically infer schemas and populate the AWS Glue Data Catalog, creating auditable, queryable metadata for all datasets. This satisfies the requirement for traceability and governance, which is especially critical in financial services environments. Glue ETL jobs allow teams to implement customizable transformation logic, including text normalization and chunking strategies optimized for foundation model context windows. AWS Glue Data Quality provides built-in rulesets for validating completeness, accuracy, and consistency. It also publishes quality metrics that can be monitored over time, meeting the requirement for ongoing data quality monitoring without building custom validation frameworks. Because AWS Glue is fully managed, it eliminates the need to manage infrastructure, scaling, or orchestration. This significantly reduces development and operational effort compared to custom Lambda pipelines or EC2-based processing. The processed and validated data can then be safely ingested into Amazon Bedrock workflows or knowledge bases.
Topics
Community Discussion
No community discussion yet for this question.