Business Problem

• Inefficient Data Retrieval: Underwriters had to manually search for relevant guidelines, wasting time and slowing decision-making. 
• Delayed Underwriting Decisions: The lack of a centralized, conversational interface led to inefficiencies in handling queries. 
• Scattered Document Access: Important documents were stored across multiple systems, making retrieval cumbersome. 
• Scaling Challenge: As the number of underwriting requests increased, manual processes became unsustainable. 

About Ledgebrook

Ledgebrook’s underwriters needed a way to quickly access underwriting guidelines and compare them with submitted documents. goML developed an AI-powered chatbot to streamline the underwriting process. 

Solution

goML developed an intelligent chatbot powered by AI and search capabilities: 

Conversational Interface for Underwriters: A chatbot was built using AWS Bedrock, enabling underwriters to retrieve policy and document information via natural language queries.

Seamless API Integration: The chatbot communicated with Ledgebrook’s existing document processing systems via AWS Lambda.

Automated Document Lookups: Integrated with OpenSearch Serverless, the chatbot fetched relevant documents instantly.

Secure & Scalable Deployment: Hosted within a VPC-based AWS infrastructure, ensuring data security and high availability. 

Policy & Document Comparison: Underwriters could compare guidelines with submitted documents stored in AWS S3 and categorized using PostgreSQL RDS.

Search & Retrieval Optimization: Document vectorization in OpenSearch improved response accuracy for underwriting queries. 

Architecture

• User: The initiator of the process, providing an input payload containing a token and a query. 
• DB (Database): Stores user data, including the aiDocumentSessionToken, potentially used for authentication or session management.
• Bedrock: Serves as the central component for orchestration and processing, handling:  
• Prompt Engineering: Formulating prompts for the RAG pipeline. 
• RAG (Retrieval Augmented Generation): The core logic for retrieving relevant information and generating responses. It interacts with:  
  S3 (Simple Storage Service): Stores the document corpus (underwriting data, document information). 
  OpenSearch: Provides indexing and search capabilities over the document corpus for efficient retrieval. 
• Webhook Endpoint: An external service that is triggered by Bedrock to deliver the final response. 
• Input Payload: The user sends an input payload (token, query) to the DB. 
• Token Retrieval: The DB verifies the token and provides the aiDocumentSessionToken to Bedrock. 
• RAG Pipeline Execution: Bedrock uses the token and query to initiate the RAG pipeline. This involves:  
• Prompt Engineering: Creating a suitable prompt for querying the document index. 
• Retrieval: Querying OpenSearch to fetch relevant documents from S3. 
• Information Extraction: Processing the retrieved documents to extract the necessary information to answer the query. 
• Response Generation: Bedrock generates a final response based on the extracted information. 
• Webhook Trigger: Bedrock triggers the Webhook endpoint, passing the final response. 
• Final Response Delivery: The Webhook endpoint delivers the final response to the user.