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. ​

Solution:

• Team GoML designed a new application, leveraging LangChain & Claude-v2 for intelligent document extraction, built on native AWS services, including Bedrock & Textract​
• The new application gave users capability to query policy documents with higher accuracy & have NLP powered interaction with Insurance documents, including intelligent analytics on insurance data, such as the highest no of premium filed within a region etc.​
• The application also automated downstream workflows, like Claims Settlement & FNoL, post data extraction, increasing the STP Claims significantly

Architecture:

Technology Stack: