Pipelines

Create and manage automated data pipelines. A pipeline is a one-directional flow that sends all data from a source system to an agent, creating a new session per source record for the agent to act on. This is distinct from agent schedules (recurring single executions) and connectors (bidirectional chat integrations like Slack).

📄️Create pipeline

Create a new pipeline that continuously ingests data from a source system and sends each record to an agent for processing. A new agent session is created per source record. A pipeline is distinct from an agent schedule (which is a recurring single execution of an agent) and from a connector (which is a bidirectional chat integration like Slack). A pipeline is an automated, one-directional flow of all source data through an agent.

📄️List pipelines

List all pipelines with optional filtering by source type, status, or enabled state.

📄️Get pipeline

Retrieve a pipeline by its key, including its current status, watermark, and configuration.

📄️Replace pipeline

Replace a pipeline's configuration. The full pipeline definition must be provided.

📄️Update pipeline

Partially update a pipeline's configuration. Omitted fields are preserved.

📄️Delete pipeline

Permanently delete a pipeline and its run history. This cancels any in-progress runs. Agent sessions created by this pipeline are not deleted.

📄️Trigger pipeline

Manually trigger a pipeline run outside of the normal schedule. The pipeline will fetch new data from the source and process it through the agent. Returns the created run.