Databricks vs BigQuery: AI features compared

Found relevant data: When applicable, shows the specific tables or data sources Genie identified as relevant to your question.

Metadata about the conversation, such as the agent and data sources used.

Genie analyzes the selected change and returns an explanation with the top contributing factors.

Conversational analytics supports the following AI and ML functions in response to chats with data agents and data sources, and in verified SQL queries that you create.

Run advanced analyses, such as statistical analysis, forecasting, and what-if scenarios.

Each set of insights shows when it was generated, such as Generated 5 minutes ago.

Create scheduled tasks to run Genie Code prompts on a schedule, so you can turn recurring analysis into a background task.

Schedule a query by providing the following details in your prompt:

Slack: Search Slack messages and channels, and send messages.

The Data Engineering Agent cannot execute pipelines. You must review and run or schedule pipelines.

Supervisor Agent uses advanced AI orchestration patterns to manage agent interactions, task delegation, and result synthesis to deliver comprehensive solutions.

Seamless orchestration: Ask a general analytical question (for example, "How is our sales pipeline trending in the last 3 months?") and Gemini Enterprise automatically routes the query to the relevant data agent.

Genie Code creates Unity Catalog metric views, and reuses existing Unity Catalog metric views that already match your data model.

You can review, edit, and publish these descriptions to Knowledge Catalog to improve data discoverability and documentation.

To edit a metric view with SQL, use ALTER VIEW with an updated YAML definition.

Ask the agent to create and transform the datasets behind a dashboard.

You can prompt Gemini in BigQuery to explain a SQL query in natural language.

"Add a custom calculation to compute the year-over-year growth rate."

You can generate SQL in the query editor by describing the query that you want in a comment.

The serialized lvdash.json file that you have after exporting a dashboard includes complete query syntax and widget settings.

That means that when you edit a dashboard file directly, you can upload that file to the original workspace and overwrite the existing file while maintaining the existing sharing settings.

For existing dashboards, open the Genie Code side panel.

The assistant works with new or existing data canvases.

Describe a dashboard in natural language, and the agent plans the work, builds it, and refines it with you, from finding data to laying out finished pages.

As the plan runs, generated code and text appear in the notebook.

The Workspace Export API GET /api/2.0/workspace/export allows you to export the contents of a dashboard as a file.

To manage BigQuery Studio saved queries by using the BigQuery API:

This tool can copy dashboard content or create new, blank dashboards.

To manage BigQuery Studio saved queries by using the BigQuery API:

When a dashboard is published with Individual data permissions, each viewer's Unity Catalog permissions determine which rows they can see.

All viewers see the rendered Data Apps based on the author's access.

To keep improving a deployed app, click Genie App Builder on the app details page.

Genie App Builder lets you build Databricks apps in the Databricks UI by describing them in natural language.

To save time, use the integrated agent to generate the code for you.

After you create the app, you can download the source code to your local machine to customize it.

Deploy the app by running the following command.

Genie Code connects to external tools, documents, and data through Model Context Protocol (MCP) servers and native connectors for Google Drive, Gmail, Google Calendar, Microsoft 365, Atlassian, Glean, Slack, and GitHub.

For lineage history beyond one year, use Catalog Explorer or the lineage API, which indefinitely retain lineage captured after September 1, 2024.

VIEW: A virtual table defined by a SQL query.

Referenced SQL example: When applicable, displays a relevant SQL example that Genie used as a reference.

Matches are always marked as verified.

Hiding a column removes it from the Genie Agents's context, so Genie won't reference it when generating SQL or answering questions.

Instructions. You can instruct a data agent to always filter data to the most recent quarter when asked about "trends," or to group results by "product category" by default.

Positive feedback on responses that join tables or use SQL expressions can prompt Genie to suggest new SQL snippets (such as measures, joins, or filters) to agent managers for review and approval.

To edit, share, or delete a data agent: Gemini Data Analytics Data Agent Owner (roles/geminidataanalytics.dataAgentOwner) on the agent or project.

Query metric views from SQL editors, notebooks, dashboards, Genie Agents, and alerts.

Create BigQuery custom glossary terms for each agent or import business glossary terms from Knowledge Catalog.

When partner-powered AI features are disabled, AI assistive features use Databricks-hosted models, which are entirely Databricks-selected and Databricks-managed.

In the Model section, choose which types of models are available to users in a conversation with the agent.

Then, you can save it as an instruction to teach Genie how to answer in the future.

If the response is not what you expect, change the settings in the Editor section to refine the data agent configuration until you get satisfactory responses.

When Genie uses a trusted asset to answer a question, it provides a verified answer, giving agent users an extra layer of confidence in the result's accuracy.

If an agent can use a verified query to answer a question that you ask it, to ensure a trustworthy answer, the agent invokes the query exactly as written.

Query system.ai_gateway.usage to analyze model requests by user, model, or workspace, including token usage, latency, and errors.

Agent metrics include agent usage, model calls, tool usage, health, latency, and token usage.

The following query returns all billed Genie usage, per user and per day.

Filter your billing report by label to understand agent costs.

Positive feedback on responses that join tables or use SQL expressions can prompt Genie to suggest new SQL snippets (such as measures, joins, or filters) to agent managers for review and approval.

- To place the data agent in draft mode, which you can re-edit later, click arrow_back Go back to return to the Agent Catalog page. Because your agent is now in draft mode, it appears in the My draft agents section on the Agent Catalog tab.

Row filters and column masks defined in Unity Catalog are automatically enforced per user.

When a user interacts with an agent, the API queries the connected data source by using that user's credentials.

Importantly, your data is not stored outside of your workspace's Geo regardless of this setting.

For these features, Gemini processing occurs in the jurisdictional boundaries of the query location, or where the BigQuery dataset is stored.

The ASK outcome pauses the call until a person approves it.

Revert a dashboard's definition in draft mode to the last published version.

BigQuery lets you query and restore data stored in BigQuery that was changed or deleted within your time travel window.

MCP rate limits apply to tools/call requests and use queries per minute (QPM).

You are still subject to the quotas enforced by the APIs called by the MCP server tools.