Databricks Opens Business Data to ChatGPT, Claude, Copilot and Grok

Databricks launched native Genie plugins on November 11, 2026 for four AI agents: ChatGPT, Claude, Microsoft Copilot Cowork and Grok Bot. The plugins give each agent governed access to business context held in Databricks, while other compatible agents can still connect through the Genie One MCP server.

For employers, the launch touches two people-process decisions at once: which workplace assistants employees may use with company data, and how governance travels with that data. A single approved metric definition can now serve every connected agent, rather than being rebuilt per tool.

What preceded the plugins?

Databricks had already connected Genie to outside assistants. A September 22, 2026 Genie One MCP announcement described governed context for assistants and coding agents over Model Context Protocol, or MCP — a protocol for connecting AI agents to external tools. The new plugins add native interfaces inside the four named products while using the same context layer.

How does Genie supply business context?

Genie Ontology combines deliberately defined metrics and business relationships with context inferred from governed tables, queries, dashboards, notebooks and other enterprise assets. It ranks that material by authority and relevance, applies permissions, and supplies the definitions, relationships and source context Genie uses to interpret a question.

After receiving a question, Genie resolves business terms, finds data the user may access, writes and runs SQL, and returns an answer with citations to Databricks sources. It can send specialized work to domain-specific Genie Agents — marketing for pipeline attribution, finance for operational costs — and can draw insights from unstructured enterprise data.

An agent can hand Genie an entire business question or request only the context it lacks before continuing with its own tools, such as editing files, drafting plans or posting to Slack. Clients supporting the MCP Apps extension display Genie's progress, visualizations, results and ontology citations in an interactive panel; other clients receive text results.

What do the workflows look like in practice?

Databricks' examples differ by product:

• A ChatGPT Dot — an always-on agent with its own computer — can monitor feature adoption against targets using a certified active-user definition, pull related support themes and post a summary to Slack.
• Claude can investigate a regional revenue shortfall with certified finance metrics, pricing memos, sales-call notes and competitor reports, then produce an analysis with citations behind each claim.
• Microsoft Copilot Cowork can use account and usage trends from Azure Databricks to populate Word briefs, Excel charts and client presentations, then wait for approval before sending anything.
• A Grok Bot growth teammate can review campaigns using governed definitions for campaign spend, qualified opportunities and pipeline, recommend budget shifts with evidence, and prepare retargeting or lifecycle campaigns after a growth lead approves them.

In each case Genie supplies the governed numbers while the agent handles documents, communications or campaign execution.

What about permissions and limits?

Unity Catalog permissions are enforced on every request, so results stay limited to what each user may access. The Genie One MCP documentation recommends on-behalf-of user OAuth authentication, which carries the end user's identity into the request; service-principal authentication is also supported for automated workloads.

Setup starts by enabling the plugin in the agent workspace. The ChatGPT and Claude plugins use default OAuth apps, letting users sign in with their Databricks accounts without an administrator creating an OAuth application.

Genie responses are asynchronous because the system searches data and executes SQL. Standard response tools truncate query results to protect the model's context window; a separate tool retrieves the full schema and rows, though very large results can still be truncated.

There is also a hard deadline. The older beta MCP endpoint reaches end of life on November 30, 2026 — roughly three weeks after the plugin launch. Requests to it will fail after that date, and affected workloads must move to the generally available Genie One MCP endpoint.

How good will the answers be?

Answer quality depends on the data estate behind the ontology. Databricks' September 1, 2026 implementation guide says Genie Ontology works on day one, but higher accuracy requires clean data, consistent entity records, useful metadata, governed metric definitions, certified assets and continuing evaluation. The guide recommends starting with one domain and strengthening its definitions, sources, governance and evaluation before expanding.

The launch gives Databricks a consistent governance layer across agents with different native strengths. As those agents move from cited analysis to approved actions, the same ontology can determine which numbers they use and which underlying enterprise data each person is allowed to see.