Amazon Comprehend

2 use cases using this technology

2published use cases

2industries

0countries on record

Document Intelligence

top AI capability

Evidence mix: High 2 · Medium 0 · Low 0 — bands are computed from each record's evidence signals.

Industry

2 use cases

Financial ServicesGenerative AIConversational AIDocument Intelligence

EXL Transforms Insurance Underwriting with Generative AI Assistant Built on Amazon Bedrock

EXL, a global data analytics and digital solutions company, built LDS Underwriting Assist, a retrieval-augmented generation chatbot integrated into its Life Digital Suite (LDS) platform to help insurers streamline the underwriting assessment and review stages that previously required underwriters to manually review hundreds of pages of documents. The service uses Anthropic Claude 3 Sonnet on Amazon Bedrock with Amazon Kendra as the chatbot interface, Amazon Textract to extract data from scanned documents, and Amazon Comprehend to analyze text and redact PII and protected health information for compliance with regulations such as India's PII guidelines. EXL tested multiple foundation models (Mistral AI, Claude 2, Sonnet 3, Amazon Titan) to minimize hallucinations before launching the service in August 2024, just 60 days after starting development. EXL reports the solution reduces underwriting processing time from several days to a few hours and has the potential to cut underwriting costs by up to 80%.

EXLAmazon Bedrock · Anthropic Claude 3 Sonnet · Amazon Kendra +2

HealthcareGenerative AILarge Language ModelsDocument Intelligence

Myriad Genetics speeds document processing with AWS GenAI Intelligent Document Processing Accelerator

Myriad Genetics partnered with the AWS Generative AI Innovation Center to replace an Amazon Textract/Comprehend pipeline with Amazon Bedrock foundation models (Nova Pro for classification, Nova Premier for extraction) using the open-source GenAI IDP Accelerator. Document classification accuracy rose from 94% to 98%, classification cost per page fell 77% (3.1 cents to 0.7 cents), and classification time fell 80% (8.5 minutes to 1.5 minutes per document). Automated key information extraction reached 90% accuracy matching the manual baseline, with a projected $132K in annual savings and 300 hours saved monthly across 9,000 prior authorizations in the Women's Health unit alone.

Myriad GeneticsAmazon Bedrock · Amazon Nova Pro · Amazon Nova Premier +2