# Build

> Build - Build agentic workflows with DataRobot using existing templates or by modifying those
> templates to suit your specific use case.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-05-01T23:10:47.699800+00:00` (UTC).

## Primary page

- [Build](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/index.html): Full documentation for this topic (HTML).

## Related documentation

- [Agentic AI](https://docs.datarobot.com/en/docs/agentic-ai/index.html): Linked from this page.
- [Quickstart](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-quickstart.html): Linked from this page.
- [DataRobot CLI](https://docs.datarobot.com/en/docs/agentic-ai/cli/index.html): Linked from this page.
- [Getting started with the DataRobot CLI](https://docs.datarobot.com/en/docs/agentic-ai/cli/getting-started.html): Linked from this page.
- [Installation](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-install.html): Linked from this page.
- [Migrate existing agents to current version](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-starter-migration.html): Linked from this page.
- [Agent components](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-overview.html): Linked from this page.
- [Agent authentication](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-authentication.html): Linked from this page.
- [Customize agents](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-development.html): Linked from this page.
- [Add Python packages](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-python-packages.html): Linked from this page.
- [Configure LLM providers in code](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-llm-providers.html): Linked from this page.
- [Configure LLM providers with metadata](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-llm-providers-metadata.html): Linked from this page.
- [Add tools to agents](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-tools-integrate.html): Linked from this page.
- [Deploy agentic tools](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-tools.html): Linked from this page.
- [DataRobot agentic skills](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-skills.html): Linked from this page.
- [Implement tracing](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-tracing-code.html): Linked from this page.
- [Access request headers](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-request-headers.html): Linked from this page.
- [Debug agents in PyCharm](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-debugging-pycharm.html): Linked from this page.
- [Debug agents in VS Code](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-debugging-vscode.html): Linked from this page.
- [Troubleshooting](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-troubleshooting.html): Linked from this page.

## Documentation content

# Build

> [!NOTE] Premium
> DataRobot's Agentic 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 Starter template repository](https://github.com/datarobot-community/datarobot-agent-application) 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](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-quickstart.html) guide. The quickstart uses the [DataRobot CLI](https://docs.datarobot.com/en/docs/agentic-ai/cli/index.html) ( `dr start`, `dr task run`) for setup and deployment—see [Getting started with the DataRobot CLI](https://docs.datarobot.com/en/docs/agentic-ai/cli/getting-started.html) if you need to install or configure the CLI first.

| Topic | Description |
| --- | --- |
| Installation | Install required components for agentic workflow development. |
| Quickstart | Build, deploy, and test agentic workflows using DataRobot's pre-built templates. |
| Migrate existing agents to current version | Move an existing Agentic Starter project from pre-11.8.1 class-based agents to the factory-based layout. |
| Agent components | Learn about the components required to create an agent using DataRobot's agent framework. |
| Agent authentication | Learn how to implement authentication in your DataRobot agentic application, covering API tokens, authorization context, OAuth 2.0, and security best practices. |
| Customize agents | Customize agent code, test locally, and deploy agentic application for production use. |
| Add Python packages | Add required Python packages to agentic application using execution environment or custom model requirements. |
| Configure LLM providers in code | Configure different LLM providers for your agentic application 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. |
| Add tools to agents | Add local tools, predefined tools, and DataRobot global tools to your agentic application, including detailed integration patterns. |
| Deploy agentic tools | Deploy global agentic tools from the DataRobot Registry to handle tasks critical to the agent application. |
| DataRobot agentic skills | Install and use DataRobot agentic skills in your agentic application. |
| Implement tracing | Add custom tracing 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. |
| 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. |
| Troubleshooting | Diagnose and resolve common issues when working with DataRobot agentic application. |