Cloudera Docs

Deploying workflows as Model Endpoints

The Cloudera AI Agent Studio deployment system transforms AI workflows into production-ready endpoints that operate as an independent services.

The deployed workflow leveraging both Cloudera AI Workbench models and a Cloudera AI Workbench application. For more information see, Models overview and Analytical Applications .

A deployed workflow consists of the following components:
  1. A Cloudera AI Workbench Model that functions as the workflow engine to run tasks.
  2. A Cloudera AI Workbench Application that provides a user interface (UI) for interacting with the workflow.

Workflows are fundamentally asynchronous. When a workflow start request is sent to a deployment, a trace ID is immediately returned to track the workflow status. Workflow deployment logs and associated telemetry are sent to the Agent Studio Agent Operations and Metrics server.

The typical workflow execution proceeds in the following order:
  1. The workflow can be initiated either by starting it from the deployed workflow Application or by sending a kickoff request directly to the model endpoint.
  2. The workflow runs asynchronously within the model deployment, simultaneously streaming events and logs to the Operations and Metrics server.
  3. The workflow status is tracked by polling the /events endpoint on the Operations and Metrics server.

For more information, see Monitoring feature in Agent Studio.