customer_support · finance · workflow
InsuranceDekho cuts customer query response time by 80% with Amazon Bedrock and RAG
InsuranceDekho's insurance advisors, especially newer ones, had to consult subject matter experts for policy-specific queries, introducing delays of a few minutes before they could respond to customers and creating a bottleneck that led to lost prospects and added costs.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Policy document ingestion
Insurance policy documents are processed by an embedding model and stored as vector embeddings in Amazon OpenSearch Service.
Tools used
Amazon BedrockAnthropic's Claude HaikuRAGAWS PrivateLinkembedding model
Outcome
InsuranceDekho's RAG chat assistant enabled insurance advisors to address customer queries autonomously without SME involvement, achieving an 80% decrease in response time and improving sales, cross-selling, and overall customer service.
Results
Time saved80%
Grounding & classification
Source type: technical build writeup
27 fields verified against source quotes, 3 dropped as unverifiable.
agent assistconversational aiknowledge searchragknowledge basepolicy documentmetric backednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describedinsuranceemployee productivityresponse time reductiontechnical build writeupcustomer supportsales opsautonomous resolutionrag answering