Which BI tools let you save a reusable AI assistant?

Quoted from Databricks’s docsData analysts configure each agent with Unity Catalog, example SQL queries, instructions, and trusted assets; business users query it through the chat UI.

Quoted from Snowflake’s docsYou define an agent as a reusable object that bundles its model, tools, and orchestration instructions.

Quoted from Omni’s docsA skill is a set of instructions you save once and reuse with the Omni Agent.

Quoted from Hex’s docsTasks themselves are single-player: only the user who created a Task can view and edit the configuration of the Task.

Quoted from Sigma’s docsInstructions and data sources provide the context, while actions and agents configured in your data platform provide the tools for an agent to take action or enrich insights.

Quoted from BigQuery’s docsData agents consist of one or more knowledge sources, and a set of instructions specific to a use case for processing that data.

Quoted from Looker’s docsCollaboration and reuse: Explore conversations are typically limited to one user, while data agents can be shared with other members of your organization.

Quoted from Tableau’s docsYou can create permission sets or profiles to control which users can access your new Analytics and Visualization agent.

Quoted from Power BI’s docsApp-scoped Copilot supports verified answers prepared by app authors.

Quoted from Metabase’s docsSystem prompts let you customize instructions for Metabot.

Quoted from Alteryx’s docs- Alteryx Agents: Build an agent to answer natural-language questions about your datasets. Select 1 or more datasets, add custom instructions and starter prompts to guide the agent's responses, and preview the agent before you share it. Agents can return trend analysis, root cause analysis, common cause analysis, and outlier detection.

Quoted from MotherDuck’s docsThis Flight shows how to build your own data-analysis agent and run it on a schedule in MotherDuck.