Genie Spaces

A Genie Space is a domain-specific natural-language chat interface in Databricks where users ask questions of their data and get back SQL queries, results tables, and visualizations. Data analysts curate each space with datasets registered to Unity Catalog, example SQL queries, SQL expressions for business semantics, and text instructions tailored to the organization's terminology.

Genie Spaces are part of the Genie family of AI experiences. Business users who want a single chat interface across data assets, dashboards, and apps should use Genie One. Developers and technical practitioners who want an AI assistant for writing code, generating pipelines, and building dashboards should use Genie Code. For privacy, trust, and security details, see Databricks AI assistive features trust and safety.

Get started

• • Genie Spaces concepts
  • Learn what Genie Spaces are, how they generate responses, and how data access works.
• • Create and manage a Genie Space
  • Create a Genie Space and configure datasets, SQL queries, and instructions.

For space authors

• • Tune Genie Space quality
  • Add metrics, business rules, and verified answers to improve response quality.
• • Test and monitor a Genie Space
  • Test your space, run benchmarks, and review Genie's performance.
• • Embed a Genie Space in an external app
  • Embed a Genie Space in an external application.
• • Curate an effective Genie Space
  • Follow recommended patterns for data selection, instructions, and space management.
• • Troubleshoot Genie Spaces
  • Diagnose and resolve common issues with your space.

For space consumers

• • Use a Genie Space to explore business data
  • Ask data questions in natural language and explore results.
• • Upload a file to a Genie Space
  • Blend local CSV and Excel files with Unity Catalog data to answer questions.

Advanced topics

• • Agent mode in Genie Spaces
  • Use Genie Spaces in agent workflows for multi-step data analysis.
• • Use the Genie Spaces API
  • Integrate Genie into applications and chatbots using the Conversation API.