Develop agentic workflows¶
Premium
DataRobot's Generative AI capabilities are a premium feature; contact your DataRobot representative for enablement information. Try this functionality for yourself in a limited capacity in the DataRobot trial experience.
The DataRobot Agentic Workflow Templates repository provides ready-to-use templates for building and deploying AI agents with multi-agent frameworks. These templates streamline the process of setting up your own agents with minimal configuration requirements and support both local development and testing, as well as deployment to production environments within DataRobot.
To start building and deploying AI agents from DataRobot-provided templates, review the Quickstart guide.
| Topic | Description |
|---|---|
| Installation | Install required components for agentic workflow development. |
| Quickstart | Build and deploy AI agents from templates leveraging multi-agent frameworks. |
| Agent components | Learn about the components required to create an agent using DataRobot's agent framework. |
| Agent authentication | Learn how to implement authentication in DataRobot agent templates, covering API tokens, authorization context, OAuth 2.0, and security best practices. |
| Use the agent CLI | Use CLI commands to test and interact with your agentic workflows during development. |
| Customize agents | Customize agent code, test locally, and deploy agentic workflows for production use. |
| Debug agents in PyCharm | Use PyCharm's Run configuration in debug mode to debug agent code locally. |
| Debug agents in VS Code | Use VS Code's Run and Debug configuration to start dev.py and step through agent code locally. |
| Add Python packages | Add required Python packages to agentic workflows using execution environment or custom model requirements. |
| Configure LLM providers in code | Configure different LLM providers for your agentic workflows including DataRobot gateway, external APIs, and custom deployments. |
| Configure LLM providers with metadata | Configure LLM providers using environment variables and Pulumi for infrastructure-level configuration without modifying agent code. |
| Deploy agentic tools | Deploy global agentic tools from the DataRobot Registry to handle tasks critical to the agent workflow. |
| Add tools to agents | Add local tools, predefined tools, and DataRobot global tools to your agentic workflows, including detailed integration patterns. |
| Implement tracing | Add OpenTelemetry tracing and custom span instrumentation to your agent tools for monitoring, debugging, and observability. |
| Access request headers | Learn how to access HTTP request headers in your deployed agents for authentication, tracking, and custom metadata. |
| Update agentic templates | Update agentic templates to include the latest features and ensure compatibility with DataRobot. |
| Troubleshooting | Diagnose and resolve common issues when working with DataRobot agentic templates. |