*This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey. We are aware some courses have accessibility limitations and are working to address. If you require accommodation, please contact [AWS Training and Certification Customer Support](https://support.aws.amazon.com/#/contacts/one-support?formId=trainingCertification).*
Learners will discover how to improve structured data extraction from unstructured documents using Amazon Bedrock Data Automation blueprints. The course covers the blueprint instruction optimization feature, which automatically refines extraction instructions using three to ten example documents with expected values -- eliminating the need for separate model fine-tuning. Participants will learn to run the optimization workflow through the Amazon Bedrock console or API, understand common challenges like format variation and poor scan quality, and apply best practices for selecting example documents and ground truth to achieve higher extraction accuracy across diverse production documents.