Databricks integration for AI agents
Run SQL, manage jobs, and ask Genie agents on Databricks
Databricks is a Sim integration in the Databases category. Sim is the AI workspace where teams build and deploy AI agents. Sim's Databricks integration provides 53 tools that AI agents can use inside Sim's visual workflow builder. Databricks connects with an API key. Free to start at sim.ai.
Last updated
What Sim agents can do with Databricks
Execute parameterized SQL and retrieve result chunks, create and manage jobs, submit and repair runs, manage compute clusters and SQL warehouses, and create or update Genie spaces. Ask Genie questions or run agent research, inspect conversations, and retrieve query results and charts. Connect with a personal access token and workspace host URL.
- Category
- Databases
- Authentication
- API key
- Tools
- 53
- Triggers
- 0
- Documentation
- Databricks docs
How to automate Databricks with Sim
Create a free account
Sign up at sim.ai in seconds. No credit card required. Your workspace is ready immediately.
Add a Databricks block
Open your workspace, drag a Databricks block onto the workflow builder, and paste in your Databricks API key.
Configure, connect, and run
Pick the tool you need, wire in an AI agent for reasoning or data transformation, and run. Your Databricks automation is live.
Agent templates
Ready-to-use templates featuring Databricks. Click any to build it instantly.
Databricks tools
53 Databricks tools available to Sim agents.
Execute SQL
Execute a SQL statement against a Databricks SQL warehouse and return results inline. Supports parameterized queries and Unity Catalog.
Get Statement
Poll a SQL statement by its ID to retrieve status and results. Use this after Execute SQL when a query runs longer than the wait timeout.
Get Statement Chunk
Retrieve one chunk of an INLINE SQL result using nextChunkIndex from Execute SQL or Get Statement.
Cancel Statement
Request cancellation of an executing SQL statement; poll Get Statement to confirm its final status.
List Jobs
List all jobs in a Databricks workspace with optional filtering by name.
Get Job
Get the full definition and settings of a single Databricks job by its job ID.
Create Job
Create a Databricks job with tasks, scheduling, execution identity, and notifications.
Update Job
Merge selected settings into a Databricks job and optionally remove settings or tasks.
Reset Job
Replace all settings of a Databricks job.
Delete Job
Delete a Databricks job and cancel its active runs.
Run Job
Trigger an existing Databricks job to run immediately with optional job-level or notebook parameters.
Submit Run
Submit a one-time task run without creating a saved job.
List Runs
List job runs in a Databricks workspace with optional filtering by job, status, and time range.
Get Run
Get the status, timing, and details of a Databricks job run by its run ID.
Get Run Output
Get the output of a completed Databricks job run, including notebook results, error messages, and logs. For multi-task jobs, use the task run ID (not the parent run ID).
Repair Run
Rerun failed or selected tasks within an existing Databricks run.
Cancel Run
Cancel a running or pending Databricks job run. Cancellation is asynchronous; poll the run status to confirm termination.
Cancel All Runs
Request cancellation of active runs of a job or queued runs in the workspace.
Delete Run
Delete a completed Databricks job run.
List Clusters
List a page of clusters in a Databricks workspace including their state, configuration, and resource details.
Get Cluster
Get the state, configuration, and resource details of a single Databricks cluster by its cluster ID.
Create Cluster
Create a compute cluster with runtime, sizing, policy, and cloud-specific settings.
Edit Cluster
Replace a compute cluster configuration; a running cluster restarts to apply the changes.
Start Cluster
Start a terminated all-purpose compute cluster.
Restart Cluster
Restart a running compute cluster.
Resize Cluster
Change the fixed worker count or autoscaling range of a running cluster.
Terminate Cluster
Terminate a compute cluster while retaining its configuration for a later restart.
Delete Cluster
Permanently delete a compute cluster and its configuration.
List Warehouses
List a page of SQL warehouses in a Databricks workspace including their size, state, and type. Use this to discover the warehouse ID needed for Execute SQL.
Get Warehouse
Get the configuration, state, and scaling settings of a SQL warehouse.
Create Warehouse
Create a SQL warehouse with sizing, autoscaling, and serverless settings.
Edit Warehouse
Update a SQL warehouse configuration.
Start Warehouse
Start a stopped SQL warehouse.
Stop Warehouse
Stop a running SQL warehouse.
Delete Warehouse
Delete a SQL warehouse.
List Genie Spaces
List the Genie spaces (Genie agents) you can access. Use this to find the space ID needed to ask Genie a question.
Get Genie Space
Get a Genie space's title, description, and SQL warehouse, optionally with its full configuration export (tables, instructions, sample questions).
Create Genie Space
Create a Genie space from its serialized configuration and a SQL warehouse.
Update Genie Space
Update a Genie space, optionally protecting the change with its current ETag.
Trash Genie Space
Move a Genie space to the trash.
Ask Genie
Ask a Databricks Genie space a question in natural language and wait for the answer. Starts a new conversation, or continues an existing one when a conversation ID is given. Returns the text answer, the SQL Genie generated, and the query result rows.
Get Genie Message
Get a Genie message's status and answer, including the generated SQL, visualizations, and suggested follow-up questions.
List Genie Messages
List the messages in a Genie conversation with their answers and generated SQL, for example to replay a conversation history.
Get Genie Query Result
Get the rows returned by the SQL query Genie generated for a message. Available once the message is EXECUTING_QUERY or COMPLETED.
Execute Genie Query
Re-run the SQL query Genie generated for a message. Use this when the message's query result has expired (status QUERY_RESULT_EXPIRED). If the returned status is PENDING or RUNNING, fetch the rows afterwards with Get Genie Query Result.
Download Genie Visualization
Download a chart Genie generated as a PNG image, for example to post it to Slack. The message must be COMPLETED and asked with visualization enabled. Not supported on Private Link workspaces.
Send Genie Feedback
Rate a Genie answer as positive or negative, with an optional comment. Space authors use this feedback to improve the space's instructions.
Delete Genie Message
Delete a message from a Genie conversation.
List Genie Conversations
List conversations in a Genie space, including whether each is a chat-mode or agent-mode conversation. By default only your own conversations are returned.
Delete Genie Conversation
Delete a Genie conversation you no longer need.
Ask Genie Agent
Ask a Genie agent a question in agent mode, where Genie plans multi-step research, runs several SQL queries, and writes a report with citations. Waits for the final report. Starts a new agent-mode conversation, or continues one when a conversation ID is given. Agent mode is in preview and must be enabled on the workspace.
List Genie Agent Items
List an agent-mode conversation's full history in order: questions, reasoning, SQL calls, query results, and reports. Agent mode is in preview and must be enabled on the workspace.
Cancel Genie Agent Response
Cancel an in-flight Genie agent response using the response ID returned by the agent stream.
Frequently asked questions
Sim's Databricks integration adds 53 tools to the AI agents you build in Sim's visual workflow builder. Run SQL, manage jobs, and ask Genie agents on Databricks.
