back_office_ops · ecommerce · workflow
Co-op builds a RAG virtual assistant on Databricks to streamline 50,000–60,000 weekly in-store policy queries
Co-op store colleagues had to navigate over 1,000 policy and procedure documents under time pressure using a traditional keyword search that was slow, required precise terms, and drove 50,000–60,000 weekly queries to support centers, raising operational costs and reducing efficiency.
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 · Colleague submits a query
Store colleagues submit policy or procedure questions through the "How Do I?" virtual assistant application.
Tools used
Databricks Data Intelligence PlatformDatabricks Lakeflow JobsDatabricks Vector SearchMLflowDBRXMistralOpenAI's Chat GPT-3.5Databricks Model ServingDatabricks AssistantAgent Bricks Custom Agents
Outcome
Initial internal test feedback is overwhelmingly positive—employees found the application intuitive and much quicker than the previous system. Co-op plans a store trial with potential for full-scale deployment.
Results
Time saved50,000 to 60,000
Volume23,000
Grounding & classification
Source type: vendor customer story
33 fields verified against source quotes.
conversational aiknowledge searchragknowledge basepolicy documentfailure mode describednamed customertools describedworkflow describedinsuranceretailcost reductiondeflection rateemployee productivityvendor customer storyback office opsautonomous resolutionrag answering