- type
- Domain-specific coding agent (data engineering / data science)
- interface
- Databricks workspace + notebooks + Lakeflow (Pipeline Editor, Lakeflow Jobs); not a standalone CLI
- openSource
- No (proprietary Databricks product, built on open-source components such as Apache Spark and Apache Iceberg)
- lineage
- Unity Catalog-grounded context selection; plans multistep data engineering/ML/BI workflows for approval before autonomous execution; writes and debugs SQL and Python pipelines
- note
- Embedded directly in the Databricks workspace rather than a separate app; distinct from the already-tracked Snowflake-native and dbt-native data harnesses
- iconUrl
- /research/harness-icons/genie-code.png
