Sign in

v3

latestOpenAPI 3.0.02026-08-081996601.2 MB
Pipelines

Create pipeline

Creates a new pipeline that continuously ingests data from a source system and sends each record to an agent for processing. Each source record creates a new agent session. A pipeline is distinct from an agent schedule, which is a recurring single execution of an agent. It is also distinct 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.

post/v2/pipelines

Headers

Request-Timeoutinteger

The platform makes a best effort to complete the request in the specified seconds, or it times out.

Request-Timeout-Millisinteger

The platform makes a best effort to complete the request in the specified milliseconds, or it times out.

Request body

keystring

The unique key for the pipeline. You can provide the key, or the platform generates one.

namestring required

The human-readable name of the pipeline.

descriptionstring
sync_mode'incremental' | 'full_refresh'

How the pipeline syncs data from the source.

  • incremental: Only process new or changed records since the last watermark.
  • full_refresh: Process all records from the source on each run.
enabledboolean
metadataobject

Example request

{
  "key": "sharepoint-legal-ingest",
  "name": "SharePoint Legal Docs Ingest",
  "source": {
    "type": "sharepoint",
    "site_url": "https://contoso.sharepoint.com/sites/legal",
    "tenant_id": "72f988bf-86f1-41af-91ab-2d7cd011db47",
    "client_id": "0a1b2c3d-4e5f-6789-abcd-ef0123456789",
    "folder_path": "/Contracts/2026"
  },
  "trigger": {
    "type": "cron",
    "expression": "0 */6 * * *"
  },
  "transform": {
    "type": "agent",
    "agent_key": "customer_support",
    "verification": {
      "type": "condition",
      "expression": "get('$.output.status') == 'success'"
    }
  }
}

Response

The created pipeline.

keystring required

The unique key for the pipeline. You can provide the key, or the platform generates one.

namestring required

The human-readable name of the pipeline.

descriptionstring

A description of what this pipeline does.

sync_mode'incremental' | 'full_refresh' required

How the pipeline syncs data from the source.

  • incremental: Only process new or changed records since the last watermark.
  • full_refresh: Process all records from the source on each run.
status'initializing' | 'active' | 'paused' | 'error' required

The current operational status of the pipeline.

status_messagestring nullable

Human-readable status details, such as an error description.

enabledboolean required

Whether the pipeline is enabled. Disabled pipelines do not run on their trigger schedule.

metadataobject

Arbitrary key-value metadata for the pipeline.

created_atstring date-time required

When the pipeline was created.

updated_atstring date-time

When the pipeline was last updated.

Example response

{
  "key": "sharepoint-legal-ingest",
  "name": "SharePoint Legal Docs Ingest",
  "description": "Ingests legal contracts from SharePoint and indexes them into the legal corpus.",
  "source": {
    "type": "sharepoint",
    "site_url": "https://contoso.sharepoint.com/sites/legal",
    "tenant_id": "72f988bf-86f1-41af-91ab-2d7cd011db47",
    "client_id": "0a1b2c3d-4e5f-6789-abcd-ef0123456789",
    "folder_path": "/Contracts/2026"
  },
  "trigger": {
    "type": "cron",
    "expression": "0 */6 * * *"
  },
  "transform": {
    "type": "agent",
    "agent_key": "customer_support",
    "verification": {
      "type": "condition",
      "expression": "get('$.output.status') == 'success'"
    }
  },
  "watermark": {
    "value": "2026-02-19T08:00:00Z"
  }
}