Wednesday, November 18, 2026

Top 5 This Week

Related Posts

Databricks offers Genie on Slack with access control | Brief AI


Databricks makes its Genie application available to everyone in Slack. The tool promises contextualized responses according to Unity Catalog rights, actions via MCP with approval and centralized administration, all without leaving the discussion threads.

Rights governance and centralized management in Slack

Every question asked of Genie in Slack is processed with the identity of the person asking it, applying Unity Catalog permissions and permissions from connected sources. In channels, responses use the questioner’s rights, and each channel can decide whether they are shared to the channel or sent privately. Workspace administrators can set default visibility for the entire workspace. AI usage is governed via Unity Gateway, with MCP policies, cost controls and monitoring functions. These policies determine which MCP servers and tools are accessible, which users are allowed, and which actions require human approval, while records keep track of what was done and by whom. Environments using Private Link are supported through context-based ingress policies, which an account administrator must create.

Contextualized answers and citation of sources

Genie responds directly in the channel, thread or private message where the question was asked, with answers rooted in the business context accessible to the user. The tool only reads content from the channels it has been invited to and responds in the context of the relevant channel. The responses are published in the thread that called the assistant, which preserves the history of the exchanges. By default, they are visible to all channel members, but administrators can set private responses as default for the entire workspace. Each answer cites its sources and allows further exploration, including in Genie One via links.

From questioning to action with MCP and planning

Genie is not limited to responses and can act in other tools thanks to MCP connectors, creating or updating documents, commenting on tickets or modifying records with user credentials. Each change is prepared for approval before execution. Users can schedule recurring scans from Slack, via a dedicated button or natural language instruction, with results delivered in their direct messages. It is possible to attach files for analysis and get documents such as PDFs back in the feed. Genie also feeds visualizations directly into Slack. These same abilities are available in Genie One.

The AI ​​brief that professionals read

We test and decipher the new AI tools every evening, in 5 minutes. Free.

Included upon registration: our selection of the best AI guides & comparisons.

Choose your pace

Free · No spam · Unsubscribe in 1 click

Implementation on the administrator side and user experience

Admins install the Databricks Genie app from the Slack Marketplace and configure channels and response visibility. Users get started by sending Genie a DM or mentioning it in a channel, then log in to Databricks on first use and choose a workspace. In channels where Genie has been added, anyone who has linked their Databricks account can invoke it and each channel can be associated with a given Databricks workspace. It is also possible to pin a channel to a specific Genie agent to frame the scope of responses.

Functional scope: Genie One by default, agents and integrations

Channels in Slack default to Genie One, which routes questions through Genie Search and Genie Agents to cover the entire data estate. The app supports Genie One and agents, and a conversation or channel can be pinned to an agent via the Genie Agentic API. Users can discover and visualize insights from Databricks data, integrate context from sources like Google Drive, Confluence or Jira, and make updates or comments via MCP after approval. Notifications from the Databricks platform can be received in Slack, and responses can be rated with a thumbs up or thumbs down. Recurring analyzes are configured either in Slack or in Databricks via scheduled tasks, with Slack as the destination, provided you have made a prior DM connection. The app is now available in general release and can run scheduled scans. Databricks presents it as a governed AI operating in Slack, where teams make decisions. Processing runs inside the Databricks workspace and the routing service does not store questions or answers. In DM, the user can query their data, search in connected knowledge and obtain results in tables or graphs, as well as upload files for analysis.

Access and additional resources

A webinar entitled “Just Ask Your Data: Bring Databricks Genie into Slack” is offered to deepen the use of the application. Results of scheduled scans are delivered via direct message in Slack. It is also possible to create scheduled tasks in Genie One by choosing Slack as the destination.

Shredder Smith
Shredder Smith
Shredder Smith is the lead curator and digital persona behind topaitools4you.com, an AI directory dedicated to "shredding" through industry hype to identify high-utility software for everyday users. Smith positions himself as a blunt, no-nonsense reviewer who vets thousands of emerging applications to filter out overpriced "wrappers" in favor of tools that offer genuine ROI and practical productivity. The site serves as a watchdog for the AI gold rush, providing categorized rankings and transparent reviews designed to help small businesses and creators navigate the crowded tech landscape without wasting money on low-value tools.

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Popular Articles