Skip to main content
Community Hub
TL;DR

Deploy a context repository in Context Engineering Studio to Databricks Genie. CES pushes descriptions into Unity Catalog, creates one Metric View per table, and configures a Genie Space. On Databricks, deploying is part of the build cycle because building and simulating both run on the live Genie Space.

Your AI can read this via Docs MCPInstall MCP →Connect

Deploy to Databricks Genie

Deploying to Databricks Genie pushes descriptions into Unity Catalog, creates one Metric View per table in your target schema, and configures a Genie Space backed by those views. On Databricks, deploying is part of the build cycle, not the end of it. Building and simulating both run on a live Genie Space, so you deploy first to create it, then refine, simulate, and re-deploy for production. Re-deploys replace existing Metric Views in place and patch the Genie Space without recreating it.

Prerequisites​

Before you begin, make sure:

Deploy your context repository​

  1. Open your context repository and click the Portability tab. Each target engine has its own card.

  2. Find the Databricks card and click Build this format. CES renders your model as Databricks metric views and a Genie space definition.

    On Databricks, an initial deploy is required before you can simulate, because simulations run on the Genie Space that this deploy creates.

  3. Click Deploy on the card. The card expands to ask where the Metric Views and Genie Space go.

  4. Set the Catalog, Schema, and Genie Space name (for example, FINANCIAL_REPORTING_BUDGETS). All three are required and must be valid identifiers.

  5. Click Deploy. CES creates the Metric Views in Unity Catalog and configures the Genie Space.

After deployment, the repository is wired to the Genie Space and ready for building, simulating, and end-user queries. See Run simulations.

Grant access and verify​

After the production deploy, grant end users access and confirm the artifacts are visible in Databricks.

  1. Grant your business users access to the Metric Views. Run in a Databricks SQL editor, replacing <consumer_group> with the group assigned to your users.

    GRANT USE CATALOG ON CATALOG <target_catalog> TO `<consumer_group>`;
    GRANT USE SCHEMA ON SCHEMA <target_catalog>.<target_schema> TO `<consumer_group>`;
    GRANT SELECT ON VIEW <target_catalog>.<target_schema>.<metric_view_name> TO `<consumer_group>`;

  2. Grant access to the Genie Space via the Databricks workspace UI.

    • Open the Genie Space in your Databricks workspace.
    • Go to Settings → Permissions.
    • Add end-user groups with CAN RUN (can ask questions) or CAN VIEW (can view conversations only).
    • Confirm end users have consumer access or the Databricks SQL workspace entitlement.

    End users don't need direct warehouse permissions. Queries run under the creator's embedded compute credentials, and Genie respects Unity Catalog row and column security.

  3. Verify the deployment by confirming in the Databricks workspace that:

    • The Metric Views appear in Unity Catalog under <target_catalog>.<target_schema>.
    • The Genie Space is listed under Genie in the workspace sidebar and is accessible.

    You can also navigate to the deployed Metric Views in the Atlan catalog. CES crawls them automatically after deployment.

Update deployed context repository​

After a repository is live, use this process to make changes without disrupting end users. The existing Metric Views and Genie Space stay active until the new version is deployed.

  1. Open the repository and go to the Overview tab.
  2. Update the linked assets or custom instructions and regenerate, or describe the change in the chat window. See Update the context repository.
  3. Re-run your question set through Run simulations to confirm nothing has regressed.
  4. Go back to Portability, rebuild the format, and click Deploy. CES replaces the existing Metric Views and patches the Genie Space in place.

Next steps​