Databricks Genie Agents
A Genie Agent is a curated agent scoped to one business area: its tables / Metric Views, documents (UC volumes), sample questions, and instructions. It answers by writing SQL on a warehouse and, in Agent mode, by searching its documents, so one turn can combine SQL results and cited files. Distinct from Genie One (databricks-data-discovery), which answers across your data without a curated Agent.
Replaces Knowledge Assistant and Supervisor Agent for docs + data. Both are legacy ("For new low-code agents over your documents and data, use Genie Agents"). Document Q&A (was a KA) = an Agent with a volume: no endpoint, no sync. Routing between data and docs (was a Supervisor over Genie + KA) = one Agent with tables + a volume. See Documents. An Agent can also attach Databricks-provided MCP connectors (Google Drive, Microsoft 365, Slack, Jira/Confluence, GitHub, ...; Beta, set up in the UI, Agent mode only). Custom MCP servers, UC functions, or other endpoints aren't supported; build a code agent (databricks-ml-training). To maintain an existing KA / Supervisor: legacy-ka-supervisor.md.
Genie Agent Lifecycle
| Phase |
Reference |
Load when |
Typical CLI |
| Create / update |
create-genie-agent.md |
Building or editing an Agent: the workflow, the serialized_space payload format, and the CLI |
discover-schema → create-space / update-space |
| Attach documents |
create-genie-agent.md § Documents |
Document Q&A, docs + data, replacing a KA / Supervisor |
volumes create → update-space → probe in Agent mode |
| Query / converse / validate |
query-genie-agent.md |
Conversation API (tables), Agent mode API (needed for documents), Metric View SQL |
start-conversation / Agent mode responses |
| Improve (inspect / diagnose / benchmark / fix) |
improve-genie-agent.md |
Working with an existing Agent: wrong/empty answers, quality tuning, benchmark evaluation |
get-space; genie-create-eval-run; update-space |
| Export / migrate |
genie-agent-cicd.md |
Export, import, cross-workspace migration, batch migration, DABs/CI-CD |
get-space → remap → create-space |
| Optimization history |
uc-persistence.md |
Setting up UC Delta tables for multi-pass optimization history (CREATE TABLE DDL only) |
|
| Legacy |
legacy-ka-supervisor.md |
Maintaining or migrating an existing Knowledge Assistant / Supervisor Agent |
knowledge-assistants / supervisor-agents |
Typical flow: create → query/validate → improve (diagnose / benchmark / fix, as needed).
Commands
An Agent is defined by a serialized_space JSON object (sources, sample questions, per-column context, instructions), kept in a local genie_agent.json and passed to the CLI. Core commands below; the lifecycle table points to the full workflow, payload schema, and flags.
databricks genie list-spaces # find Agents
databricks genie get-space SPACE_ID --include-serialized-space # inspect config
databricks genie create-space WAREHOUSE_ID "$(jq -c . genie_agent.json)" \
--title "..." --parent-path /Workspace/Users/you@company.com/genie_spaces # create
databricks genie update-space SPACE_ID --serialized-space "$(jq -c . genie_agent.json)" # full-replace edit
databricks genie start-conversation --no-wait SPACE_ID "a question" # converse / validate (tables only)
databricks genie trash-space SPACE_ID # delete
Documents (replaces KA and Supervisor)
Attach a managed UC volume in data_sources.volumes[]: create-space / update-space start indexing automatically, and documents are read in Agent mode only (the chat-mode start-conversation ignores them). Setup, waiting for indexing, adding documents to an existing Agent, permissions, limits, and evaluation: create-genie-agent.md § Documents.
Prerequisites
- Tables / Metric Views in Unity Catalog and/or a managed UC volume of documents
- SQL Warehouse to execute queries (auto-detected if not specified)
Related Skills
1---2name: databricks-genie-agents3description: "Create, manage, and query Databricks Genie Agents (formerly Genie Spaces): curated agents over Unity Catalog tables, Metric Views, and documents in UC volumes. Use when building, migrating, tuning, or asking a specific Agent, and for document Q&A or docs + data agents (replaces the legacy Knowledge Assistant and Supervisor Agent). For data questions across the workspace, use databricks-data-discovery."4compatibility: Requires databricks CLI (>= v1.0.0)5metadata:6 source: https://skillmd.com/skills/stanfish06/databricks-genie-agents7 version: "0.2.0"8---910# Databricks Genie Agents1112A Genie Agent is a **curated agent scoped to one business area**: its tables / Metric Views, documents (UC volumes), sample questions, and instructions. It answers by writing SQL on a warehouse and, in Agent mode, by searching its documents, so one turn can combine SQL results and cited files. Distinct from **Genie One** (`databricks-data-discovery`), which answers across your data without a curated Agent.1314> **Replaces Knowledge Assistant and Supervisor Agent for docs + data.** Both are [legacy](https://docs.databricks.com/generative-ai/agent-bricks/knowledge-assistant) (*"For new low-code agents over your documents and data, use Genie Agents"*). Document Q&A (was a KA) = an Agent with a volume: no endpoint, no sync. Routing between data and docs (was a Supervisor over Genie + KA) = one Agent with tables + a volume. See [Documents](references/create-genie-agent.md#documents-uc-volumes). An Agent can also attach Databricks-provided MCP connectors (Google Drive, Microsoft 365, Slack, Jira/Confluence, GitHub, ...; [Beta](https://docs.databricks.com/genie-agents/external-tools), set up in the UI, Agent mode only). Custom MCP servers, UC functions, or other endpoints aren't supported; build a code agent (`databricks-ml-training`). To maintain an existing KA / Supervisor: [legacy-ka-supervisor.md](references/legacy-ka-supervisor.md).1516## Genie Agent Lifecycle1718| Phase | Reference | Load when | Typical CLI |19|-------|-----------|-----------|-------------|20| **Create / update** | [create-genie-agent.md](references/create-genie-agent.md) | Building or editing an Agent: the workflow, the `serialized_space` payload format, and the CLI | `discover-schema` → `create-space` / `update-space` |21| **Attach documents** | [create-genie-agent.md § Documents](references/create-genie-agent.md#documents-uc-volumes) | Document Q&A, docs + data, replacing a KA / Supervisor | `volumes create` → `update-space` → probe in Agent mode |22| **Query / converse / validate** | [query-genie-agent.md](references/query-genie-agent.md) | Conversation API (tables), Agent mode API (needed for documents), Metric View SQL | `start-conversation` / Agent mode `responses` |23| **Improve** (inspect / diagnose / benchmark / fix) | [improve-genie-agent.md](references/improve-genie-agent.md) | Working with an existing Agent: wrong/empty answers, quality tuning, benchmark evaluation | `get-space`; `genie-create-eval-run`; `update-space` |24| **Export / migrate** | [genie-agent-cicd.md](references/genie-agent-cicd.md) | Export, import, cross-workspace migration, batch migration, DABs/CI-CD | `get-space` → remap → `create-space` |25| Optimization history | [uc-persistence.md](references/uc-persistence.md) | Setting up UC Delta tables for multi-pass optimization history (CREATE TABLE DDL only) | |26| Legacy | [legacy-ka-supervisor.md](references/legacy-ka-supervisor.md) | Maintaining or migrating an **existing** Knowledge Assistant / Supervisor Agent | `knowledge-assistants` / `supervisor-agents` |2728Typical flow: **create → query/validate → improve** (diagnose / benchmark / fix, as needed).2930## Commands3132An Agent is defined by a **`serialized_space`** JSON object (sources, sample questions, per-column context, instructions), kept in a local `genie_agent.json` and passed to the CLI. Core commands below; the lifecycle table points to the full workflow, payload schema, and flags.3334```bash35databricks genie list-spaces # find Agents36databricks genie get-space SPACE_ID --include-serialized-space # inspect config37databricks genie create-space WAREHOUSE_ID "$(jq -c . genie_agent.json)" \38 --title "..." --parent-path /Workspace/Users/you@company.com/genie_spaces # create39databricks genie update-space SPACE_ID --serialized-space "$(jq -c . genie_agent.json)" # full-replace edit40databricks genie start-conversation --no-wait SPACE_ID "a question" # converse / validate (tables only)41databricks genie trash-space SPACE_ID # delete42```4344## Documents (replaces KA and Supervisor)4546Attach a managed UC volume in `data_sources.volumes[]`: `create-space` / `update-space` start indexing automatically, and documents are read in Agent mode only (the chat-mode `start-conversation` ignores them). Setup, waiting for indexing, adding documents to an existing Agent, permissions, limits, and evaluation: [create-genie-agent.md § Documents](references/create-genie-agent.md#documents-uc-volumes).4748## Prerequisites4950- **Tables / Metric Views in Unity Catalog** and/or a **managed UC volume** of documents51- **SQL Warehouse** to execute queries (auto-detected if not specified)5253## Related Skills5455- **[databricks-data-discovery](../databricks-data-discovery/SKILL.md)**: general natural-language data exploration / "ask Genie" (Genie One) across your data, when you are not targeting a specific curated Genie Agent56- **[databricks-metric-views](../databricks-metric-views/SKILL.md)**: governed business metrics that Genie consumes. See its [SKILL.md](../databricks-metric-views/SKILL.md) for design rules that affect Genie answer quality, and [query-patterns.md](../databricks-metric-views/references/query-patterns.md) for the `MEASURE()` query rules Genie follows.57- **[databricks-unstructured-pdf-generation](../databricks-unstructured-pdf-generation/SKILL.md)**: generate demo / eval PDFs to attach to an Agent as a volume58- **[databricks-ml-training](../databricks-ml-training/SKILL.md)**: code agents (`ResponsesAgent`) when you need orchestration Genie can't express59- **[databricks-unity-catalog](../databricks-unity-catalog/SKILL.md)**: manage the catalogs, schemas, tables, and volumes Genie uses