sales_ops · saas · workflow
Building Reffy: a RAG-based agent for Databricks sales and marketing to discover 2,400+ customer stories
Databricks sales and marketing teams could not efficiently find the right customer story at the right time — thousands of references were scattered across YouTube, databricks.com, LinkedIn, Medium, and internal slides with no unified search, story quality was opaque, and discovery relied on tribal knowledge, causing high-value references to be overused and relevant newer stories to be missed.
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 · Multi-source story collection
The ETL pipeline collects text from YouTube transcripts, LinkedIn and Medium articles, public customer stories on databricks.com, and internal Google Slides and Docs.
Tools used
ReffyLakeflow JobsUnity CatalogDelta LakeAI FunctionsGemini 2.5Databricks Vector SearchDSPyMLflowDatabricks Model ServingAgent FrameworkReactFastAPILakebaseAI/BI DashboardDatabricks AppsDatabricks Asset BundlesGitHub Actions
Outcome
Reffy was adopted by over 1,800 Databricks sales and marketing employees who ran upward of 7,500 queries in its first two months, delivering more relevant and consistent storytelling, faster campaign execution, and confident at-scale use of customer proof.
Results
Time savedover 1,800
Volumeupward of 7,500
Cost replacedsaving on infrastructure costs compared to GPUs
Grounding & classification
Source type: technical build writeup
44 fields verified against source quotes.
ai agentdata extractiondocument classificationknowledge searchragsummarizationknowledge basemetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareemployee productivitytime savedtechnical build writeupmarketing opssales opsagentic task executionrag answering