Amazon Web Services announced Amazon Bedrock Data Automation (BDA), a unified API service for extracting meaningful insights from multimodal documents, images, videos, and audio files (AWS Machine Learning Blog). Unlike traditional OCR solutions that only extract text, BDA understands document context, validates extracted data, and provides confidence scores for accuracy (AWS Machine Learning Blog). The service processes documents through automated classification, extraction, normalization, and validation, supporting file formats up to 3,000 pages and 500 MB per API request (AWS Machine Learning Blog).
For commerce and operations teams, BDA removes manual document sorting and orchestration overhead that traditionally increases processing time and costs across invoices, insurance claims, legal contracts, and medical records (AWS Machine Learning Blog). The service integrates with AWS Step Functions for workflow orchestration, Amazon DynamoDB for metadata tracking, and Amazon Bedrock Knowledge Bases for semantic search and retrieval-augmented generation, enabling end-to-end document intelligence at scale (AWS Machine Learning Blog). BDA also extracts insights from visual elements—charts, graphs, diagrams—that traditional OCR cannot interpret, generating captions, data points, and structural relationships for downstream analysis (AWS Machine Learning Blog).