Databricks launches Genie for Slack with governed approvals

By Priya Raman

On November 12, 2026, Databricks announced general availability of its Genie app for Slack, adding a permission-aware interface for data questions, file analysis, charts, scheduled analyses and approved actions in connected tools. The release puts governed data and external actions inside workplace conversations, making visibility and approval settings employer deployment choices.

Employees can message Genie directly or mention @Genie in a channel or group direct message. Answers remain in the relevant conversation or thread, cite their sources and open in Databricks for more context. Google Drive, Confluence and Jira can serve as connected enterprise knowledge sources.

What can Genie access?

Genie One is the default scope, routing requests across the connected data estate. A conversation or channel can instead be pinned to a curated Genie Agent, restricting answers to that agent’s data and instructions. Channel owners select the connected Databricks workspace, public or private response visibility and the applicable Genie scope.

How do external actions get approved?

Through MCP connectors to external tools, Genie can create or modify documents, comment on tickets and update records under the requesting user’s credentials. It prepares each change for approval before execution. Only the person who asked the question can approve or deny the action; where a scope selector appears, approval can apply once, always within that chat, or always.

Genie also accepts uploaded files, returns documents such as PDFs, and renders tables and charts in Slack. Recurring analyses can be created in natural language or with a scheduling button beneath an answer, with results delivered to the requester’s Genie direct message. One presentation limit remains: “charts do not appear when response visibility is private.”

Who can see an answer?

Genie evaluates each request under the asker’s identity. Unity Catalog and connected-source permissions limit which information it may retrieve, but those retrieval controls do not automatically limit the Slack audience. Public responses, the default, remain visible to every channel or group-DM member, including people who cannot access the underlying data.

Administrators can set visibility for an individual, a channel or an entire workspace. Workspace settings override channel-wide settings, which override personal choices, and administrators can require every response to remain private. That separation creates a specific management task: verify who can retrieve the source and who can read the answer.

Where does message processing occur?

Question processing and answer generation occur in the customer’s Databricks workspace, and conversation history is stored in that workspace’s region. The central service relaying messages with Slack neither persists nor logs request or answer content; it stores only the mapping between the Slack and Databricks workspaces. The workspace’s geography and cross-geography processing setting determine where large-language-model processing occurs.

What controls govern deployment?

Unity Gateway provides centralized MCP policies, cost controls and monitoring. Its traces record Genie actions and the users who requested them, while audit logs identify Slack as the request origin separately from Databricks web and Microsoft Teams activity. Installation requires a Slack workspace administrator; afterward, users authenticate to Databricks and select a workspace.

Workspaces using Private Link also require an account administrator to configure a context-based ingress rule for the app. Genie automatically selects a SQL warehouse the requesting user can access, so employees cannot choose a compute target. Slack users also cannot create Genie agents; pinning a specific agent affects only new conversations.

What should employers test before rollout?

Databricks warns that its agents “can generate inaccurate responses” and tells users to “verify output before acting on it.” Those warnings matter where Genie can change records, comment on tickets or alter documents. The immediate adoption question is whether public visibility and approval scope fit each employer’s review process and delegation rules.

The release turns Slack into another front end for Databricks’ existing governance model. The next test for employers is whether retrieval permissions, audience settings and approval scopes remain aligned as Genie moves from answers to approved changes across connected systems.