Loading integration
Enterprise access
Agent Serve is available to teams by invitation. Tell us what you want to build and we will set up your workspace with you.
Agent Serve · Observability integration
Orchestrate data pipelines and manage job runs with Dagster
Dagster is a Observability integration for Agent Serve, the AI workspace where teams build and deploy AI agents. Agent Serve's Dagster integration provides 19 Dagster tools that AI agents can use inside Agent Serve's visual workflow builder. Dagster connects with an API key. Explore deployment options with the Agent Serve team.
Last updated
Connect to a Dagster instance to launch job runs, monitor run status, list available jobs across repositories, terminate or delete runs, reexecute failed runs, fetch run logs, and manage schedules and sensors. API token only required for Dagster+.
Agent Serve accounts are created by invitation. Request access for your team, or accept an invitation from your workspace admin, then sign in.
Open your workspace, drag a Dagster block onto the workflow builder, and paste in your Dagster API key.
Pick the tool you need, wire in an AI agent for reasoning or data transformation, and run. Your Dagster automation is live.
19 Dagster tools available in Agent Serve.
Launch a job run on a Dagster instance.
Get the status and details of a Dagster run by its ID.
Fetch execution event logs for a Dagster run.
List Dagster runs with optional filters by job name, status, and creation-time range, plus cursor pagination.
List all jobs across repositories in a Dagster instance.
Reexecute an existing Dagster run, optionally resuming only from failed steps.
Terminate an in-progress Dagster run.
Permanently delete a Dagster run record.
List all schedules in a Dagster repository, optionally filtered by status.
Enable (start) a schedule in a Dagster repository.
Disable (stop) a running schedule in Dagster.
List all sensors in a Dagster repository, optionally filtered by status.
Enable (start) a sensor in a Dagster repository.
Disable (stop) a running sensor in Dagster.
List assets tracked by a Dagster instance, optionally filtered by key prefix.
Get an asset definition and its latest materialization by asset key.
Materialize selected assets by launching their asset job with an asset selection.
Report an external (runless) materialization or observation for an asset.
DESTRUCTIVE: permanently wipes ALL materialization history (every partition) for an asset. This cannot be undone.
Ready-to-use templates featuring Dagster. Click any to build it instantly.
Agent Serve's Dagster integration adds 19 Dagster tools to the AI agents you build in Agent Serve's visual workflow builder — you build it all visually. Orchestrate data pipelines and manage job runs with Dagster. Teams often pair Dagster with Affinity and Rippling in the same agent.
Agent Serve is available to teams by invitation. Request access and the team will map out the Dagster agents, connections, and team access your process needs.