DataRobot Agent Workforce Platform overview¶

The DataRobot Agent Workforce Platform provides a unified experience for building, operating, and governing enterprise AI solutions—predictive models, generative AI, and AI agents alike.

It is available on managed SaaS, virtual private cloud, or self-managed infrastructure—including on-prem and private GPU clouds, sovereign GPU clouds, air-gapped environments, and major public cloud platforms, co-engineered with NVIDIA and validated across infrastructure from Dell and Nebius.

Governance in DataRobot operates at three layers:

1. AI and agentic governance (approval workflows and versioning before an agent ships, plus real-time moderation that catches bias, hallucinations, prompt injection, and PII leakage in production).

2. IT governance (agent-specific identity and entitlements, with consistent lineage across agents, tools, and applications).

3. Infrastructure governance (gateways, fair-use policies, and cost controls that keep spend predictable at scale).

The same governance, monitoring, and control apply wherever it runs.

Workbench¶

Building great AI solutions—predictive models, generative AI, and agentic workflows—requires a lot of experimentation. Use Workbench to quickly experiment, easily compare across experiments, and organize all your experiment assets in an intuitive Use Case container.

Registry¶

Use Registry to create deployment-ready model and agent packages and generate compliance documentation for enterprise governance.

Registry ensures that all your AI assets are documented and under version control. With test results and metadata stored alongside each AI asset, you can deploy to production with confidence, regardless of whether the asset originated with DataRobot, was user-defined, was brought in from an external framework, or is an agent built with a third-party tool such as CrewAI, LangGraph, or LlamaIndex.

Console¶

Use Console to view the operating status of every deployed model and agent.

As your organization becomes more AI-driven, you'll have tens or even hundreds of task-specific models and agents running at once. Console provides a centralized hub for observing their performance, tracing agent decisions and tool calls back to their inputs, and configuring automated intervention and notification options to keep everything running smoothly and within policy.

One-click deployments¶

But where do deployments fit into the structure above? The deployment process is your model's or agent's seamless transition from Registry to Console. Once it's registered and tested in Registry, you'll have the option to deploy it with a single click.

Once you click to deploy, DataRobot's automation creates an API endpoint in your selected prediction or runtime environment and configures all the observability, monitoring, and governance controls for it.

All four of these deployment options are supported:

• A DataRobot model to a DataRobot serverless or dedicated prediction server.
• A DataRobot model to an external prediction server.
• A custom model to a DataRobot serverless or dedicated prediction server.
• A custom model to an external prediction server.

Agentic AI deployments follow the same registered, governed path into production.

Generative AI and agentic AI¶

DataRobot's generative AI capabilities build on DataRobot's predictive AI experience, and its agentic AI capabilities build on both. Bring your favorite libraries and frameworks (CrewAI, LangGraph, LlamaIndex, or a generic template of your own), choose your LLMs and vector databases, and integrate third-party tools—then embed or deploy the result wherever it drives value for your business, with governance built in at every layer.

Inside DataRobot there is very little distinction between predictive, generative, and agentic AI. The same underlying platform (Workbench, Registry, Console) supports building, operating, and governing all three. But you'll find that tutorials and examples are still organized along these lines, since the workflows differ:

• Predictive AI includes time series, classification, regression, and unsupervised machine learning such as anomaly detection and clustering.

• Generative AI (GenAI) includes text and image generation using foundation models, typically as a single LLM call or RAG pipeline.

• Agentic AI orchestrates LLMs, tools, and predictive models into multi-step workflows: an agent plans, calls tools (including your deployed predictive models), and acts on connected systems, with tracing and governance applied at each step.

Agentic AI in DataRobot

Applications¶

DataRobot offers various approaches for building applications that allow you to share machine learning projects, generative AI workflows, and agents: custom applications, application templates, and no-code applications.

• Custom applications are a simple method for building and running custom code.
• Customizable application templates assist you by programmatically generating DataRobot resources that support your use case.
• No-code applications enable core DataRobot services without having to build and evaluate models.

Experiment with the Talk to my Data Agent application template

Which experience should you choose?¶

When working in DataRobot, you have two interface choices:

1. Log in to the platform via web browser and work with the graphical user interface (UI).
2. Access the platform programmatically with the REST API or Python client packages, or build agents with the DataRobot CLI in your own development environment (IDE, notebook, or coding agent of choice).

If you're leaning toward using DataRobot programmatically, explore the workflows in the UI first. DataRobot is committed to full accessibility in both interfaces, so you are not locked into a single choice. You can:

• Flexibly switch between code and UI at any time.
• Seamlessly collaborate with other users who are working with a different option.
• When in code, use any development environment of your choice, and bring agents built elsewhere in for governance and deployment.

Try the UI¶

An intuitive UI-based product comprised of Workbench for experiment-based iterative workflows, Registry for model evolution tracking and the centralized management of versioned models, and Console for monitoring and managing deployed models. The UI provides a complete AI lifecycle platform, with broad interoperability and end-to-end capabilities for ML experimentation and production. It is also the gateway for creating GenAI experiments, Notebooks, and applications.

Try a basic predictive walkthrough

Code¶

A programmatic alternative for accessing DataRobot using the REST API or Python client packages, or the DataRobot CLI for agent development. You can also install DataRobot agentic skills in Cursor, Claude Code, Gemini CLI, and other coding agents to bring platform workflows into your IDE.

See the Developer quickstart

Where to get help¶

Help is everywhere you look:

Next steps¶

So what's next? The best way to learn DataRobot is hands-on. Take an hour to complete these two suggested exercises.