TechPrufer
Get started
DataRobot
DataRobot logoDataRobot · Feature trail

Workload API for AI Services

1 post · Jul 2026 – Aug 2026

What this trail covers

The Workload API provides a unified layer for deploying and governing AI services, abstracting away Kubernetes complexity. It allows developers to deploy containerized AI workloads (agents, inference servers, RAG pipelines) with a single command, offering autoscaling, monitoring, and secure credential management. The API supports various AI service types and integrates with NVIDIA NIM and Hugging Face models. Day-two operations like promotion to production, diagnostics, observability, and access control are managed through this API. DataRobot OpenCode leverages this API to provide a flexible coding agent that supports model choice across closed, open, and bring-your-own options, ensuring rigorous governance and simplifying the adoption of new models.

All DataRobot trails
  1. Stop managing infrastructure: A new way to deploy AI agents and modelsThis post announces the general availability of the Workload API, a system designed to simplify the deployment and management of AI services by abstracting Kubernetes. It introduces the core concepts of Artifacts, Workloads, and Protons, and provides a detailed example of deploying an AI agent using a spec file and the DataRobot CLI. The post highlights the API's ability to integrate with NVIDIA NIM and Hugging Face models, and outlines how day-two operations like promotion to production, diagnostics, observability, and access control are handled through the same API, eliminating the need for direct Kubernetes interaction.
  2. DataRobot OpenCode: your coding agent, your model choiceThis post introduces DataRobot OpenCode, a coding agent that integrates with the DataRobot LLM Gateway. The key technical contribution is its ability to support model choice (closed, open-weight, BYO) through a unified, governed entry point, simplifying the process of adopting new models without switching tools. It leverages existing DataRobot agent skills and the CLI for installation and model selection, demonstrating a flexible approach to AI service deployment.