Genie One just got a major set of updates across context, data access, collaboration, and automation. 🧞 Here's what you can do now: • Ask questions with business-aware context built in. Genie Ontology is enabled by default • Apply your org's data conventions to every prompt with workspace instructions • Upload Word docs, images, CSVs, spreadsheets, and PDFs directly into your workflow • Query Unity Catalog tables inside Genie with schema preview and one-click access requests • Automate recurring work with scheduled tasks that reference past runs for consistent outputs @YoussefMrini walks through all of it in under 3 minutes:

Genie One MCP is a new way to bring governed business context into the AI assistants and coding agents your teams already use. It connects MCP-compatible clients like ChatGPT, Claude and Microsoft Copilot to Genie One, so they can work with approved definitions, trusted data relationships and permission-aware access. Our latest walkthrough covers how to set it up, how identity and access controls work, and best practices for managing and monitoring it in production:

Databricks Genie One MCP is now generally available! Teams working in ChatGPT, Claude, Cursor, or custom agents can now use one interface to access structured and unstructured data, insights, and answers from Genie One, grounded in governed business context from Genie Ontology. Key highlights: • 𝐂𝐨𝐧𝐬𝐢𝐬𝐭𝐞𝐧𝐭 𝐛𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐜𝐨𝐧𝐭𝐞𝐱𝐭 across agents, with shared definitions and domain semantics • 𝐑𝐢𝐜𝐡, 𝐝𝐚𝐭𝐚-𝐬𝐦𝐚𝐫𝐭 𝐞𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐜𝐞𝐬 including questions, results, visualizations, and Genie Ontology citations • 𝐂𝐞𝐧𝐭𝐫𝐚𝐥𝐢𝐳𝐞𝐝 𝐠𝐨𝐯𝐞𝐫𝐧𝐚𝐧𝐜𝐞 through Unity Gateway, with fine-grained policies and audit logging Genie One MCP brings trusted business context into the tools teams already use.

Enable Databricks Genie One to search the web, retrieve granular web data, structure it into fields, and stream it into you tables. In seconds. Learn more about Nimble's integration with Genie One ⬇️

We found and eliminated an estimated $1.2M a year in wasted AI spend and lost productivity in one hour. Here's how 👇 Using Unity Gateway tracing and Genie One, we identified seven small MCP-server bugs that were quietly driving: • ~$499K/year in wasted tokens • ~12,000 engineering hours/year in agent wait time • 1,409 tool errors in a single 24-hour window Genie One turned the trace data into a ranked list of what to fix, and a coding agent helped close the loop in an hour.

Getting an answer is only the start. The next step is turning that insight into something you can share, reuse, and act on. Genie One is adding more ways to keep that work in one place: • Turn conversations into collaborative documents • Save repeatable workflows as Genie Agents • Bring in more enterprise context with Genie Ontology snippets and file uploads • Take actions through connected MCP tools There’s also a new desktop app, so Genie One is easier to keep close while you work. Learn more: