Claude-powered Insurance Policy and Claims settlement automation

Business Problem

  • The client is a $4B IT Services provider & had an insurance product powering the Insurance lifecycle, including Policy Querying, FNoL & Claims Settlement.
  • Using traditional ML models for document text extraction & workflow-based automation, made the process slow & less accurate, with Claims STP less than 12%, quite below the industry standards.
  • Application built on legacy technology hosted in their DCs, with nonnative components, resulted in high hosting & application maintenance costs.


Claude-powered Insurance Policy and Claims settlement automation
Click to View in Full Size


  • Document Upload and Ingestion: Users upload documents, which are ingested into the system for processing.
  • AI-Powered Attribute Extraction: Amazon Bedrock and Anthropic Claude-v2 models process documents, extracting key attributes using natural language understanding.
  • Data Storage: AWS S3 provides scalable storage for ingested documents and extracted data, ensuring secure and easy retrieval.
  • Search and Retrieval: A search module enables efficient search and retrieval of documents and data using indexed attributes.
  • Data Analytics and Dashboard: A dashboard visualizes data analytics, monitors system performance, and provides access to processed documents and attributes.
  • API Integration: API Gateway manages requests between the frontend and backend, with FastAPI handling document processing and data retrieval.
  • Security and Monitoring: AWS Cloud Security ensures data protection, while SNS and CloudWatch provide notifications and monitor system performance.


STP claims, up from
12% in 3 months


Increased CSAT for post-sales support with policy query automation


Reduction in post-sales call center team in 3 months

Technology Stack​