customer_support · finance · workflow
Santalucía Seguros builds enterprise-level RAG Virtual Assistant for insurance agents on Databricks
Insurance agents at Santalucía Seguros needed to access large volumes of documentation spread across multiple locations and formats to answer customer queries quickly, while customers demanded personalized, fast, and efficient service.
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 · Agent queries VA in Teams
Insurance agents access the Virtual Assistant within Microsoft Teams to ask questions in natural language on any device, with 24/7 availability.
Tools used
DatabricksMicrosoft Teams · partnerRAGMLflowDatabricks Model ServingGPT-4Azure OpenAI APIAzure Key vaultDatabricks Marketplace
Outcome
The GenAI-based Virtual Assistant exceeded user expectations, enabling agents to answer customer coverage queries in seconds, positively impacting customer satisfaction, and accelerating product sales.
Results
Time savedanswer in seconds
Grounding & classification
Source type: technical build writeup
30 fields verified against source quotes, 1 dropped as unverifiable.
conversational aiknowledge searchragknowledge basepolicy documentnamed customerproduction runtime claimedsource backedtools describedinsurancecustomer satisfactionemployee productivityresponse time reductiontechnical build writeupcustomer supportrag answering