{"slug":"zapier-powers-real-time-customer-experiences-with-databricks","url":"https://findausecase.com/use-cases/zapier-powers-real-time-customer-experiences-with-databricks","title":"Zapier Powers Real-Time Customer Experiences with Databricks","description":"Zapier unified its data on the Databricks Platform to enable self-serve, AI-powered analytics across product, marketing, sales and support. Using the Databricks MCP connector built on Unity Catalog, AI agents get governed real-time access to Zapier's data; Vector Search handles over 600k requests per day for semantic search and RAG-based knowledge retrieval; MLflow and Model Serving operationalize ML workflows. Dashboard creation time dropped from 2-3 days to a few hours, and the share of data queries executed via AI-assisted workflows grew from 0% to roughly 75% within 6-9 months.","company":"Zapier","industry":"Technology & Software","aiCapabilities":["Retrieval-Augmented Generation","AI Model Development & MLOps"],"technology":["Databricks Platform","Databricks MCP connector","Unity Catalog","Vector Search","MLflow","Model Serving"],"deployment":"Public Cloud","problemStatement":"Zapier's legacy data stack — including its AWS Redshift data warehouse — created bottlenecks: siloed systems and heavy reliance on one insights team limited what could be explored or built, high latency made real-time personalization and responsive product experiences hard to achieve without separate systems, and many potential use cases were never attempted because integrating and maintaining additional technologies was costly and slow relative to the expected return.","solutionApproach":"Zapier adopted the Databricks Platform to unify its data and make it self-serve across the business. Through the Databricks MCP connector, built on Unity Catalog, AI agents get governed, real-time access to Zapier's data under the same fine-grained permissions as human users. Vector Search indexes and retrieves structured and unstructured data at scale to power semantic search and RAG-based knowledge retrieval, while MLflow and Model Serving operationalize machine learning workflows, from experiment tracking to production model deployment.","businessValue":"Zapier reduced dashboard creation time from 2-3 days to a few hours, achieved up to 10x faster turnaround for analytics workflows, and saw the share of data queries executed via AI-assisted workflows grow from 0% to roughly 75% within 6-9 months. Vector Search handles over 600k requests per day.","evidence":{"band":"high"},"sourceUrl":"https://www.databricks.com/customers/zapier","dates":{"publishedAt":"2026-08-16T09:36:42.740Z","publishedAtSource":"ledger","updatedAt":"2026-08-26T09:41:42.965Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/zapier-powers-real-time-customer-experiences-with-databricks. Bulk republication requires permission."}