Databricks makes Genie in Slack generally available

Databricks has made its Genie app for Slack generally available, allowing users to ask governed questions in channels, threads and direct messages without leaving Slack. Genie can also analyze files, schedule recurring reports and prepare approved changes in connected tools.
- Genie in Slack is generally available.
- Users can ask questions in channels, threads and direct messages.
- Genie cites sources and follows Unity Catalog and source permissions.
- MCP connectors support approved updates to documents, tickets and records.
- Users can schedule analyses and receive results in Slack direct messages.
Answers grounded in business context
Genie responds to questions using the business context and permissions available through Databricks Unity Catalog and connected source systems. Users can start a direct message with Genie or mention it in a Slack channel, where it replies in the relevant thread.
Every answer cites its sources. Users can review the context used to produce a result in Slack or open a source in Genie One for a deeper look. Genie can return answers, tables and charts from Databricks data, while also searching connected enterprise sources such as Google Drive, Confluence and Jira.
In channels, follow-up questions retain the thread's context. Responses are visible to everyone in the channel by default, although workspace administrators can make responses private to the person who asked. Each channel can also be connected to a selected Databricks workspace and configured to use Genie One or a specific Genie Agent.
From analysis to approved action
Databricks positions the Slack integration as a way to move from an answer to work without switching systems. Through MCP connectors, Genie can create or update documents, comment on tickets and update records using the user's credentials. It prepares each change for approval before carrying it out.
Users can ask Genie to run an analysis repeatedly, or select “Run this analysis on a schedule” beneath an answer. The results are delivered in a Genie direct message. Databricks gives the example, “Send me this analysis every Monday at 9 AM.” Users can also attach files for analysis and receive documents such as PDFs in the thread, while charts can be shared directly in Slack.
These capabilities are also available in Genie One, allowing users to review and coordinate workflows from either Slack or Databricks.
Permissions and administration remain central
According to Databricks, every question runs using the identity of the person who asked it. Unity Catalog permissions and permissions from connected sources therefore determine which information Genie can use, including when questions are asked in shared channels.
Administrators can control AI use through Unity Gateway, including MCP policies, cost controls and monitoring. MCP policies determine which servers and tools Genie can access, which users can use them and which actions need human approval. Traces record what Genie did and who requested it. Databricks also says workspaces using Private Link are supported through context-based ingress policies.
How teams can start using Genie in Slack
Administrators can install the Databricks Genie app from the Slack Marketplace and configure channels and response visibility. Users then send Genie a direct message or mention it in a channel. The first time they use the app, they sign in to Databricks and select a workspace.
Genie One is the default and can route questions across the data estate. Teams can instead pin a channel or conversation to a Genie Agent when answers need to remain within that agent's curated data and instructions. The integration brings data questions, shared discussion and approved follow-up actions into the same Slack workspace, while retaining Databricks' existing governance model.


