> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/ai-workbench/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/ai-workbench/_mcp/server.

# Quickstarts and Walkthroughs

Use this section to get started with [NVIDIA AI Workbench](/ai-workbench/overview/introduction). These quickstarts and walkthroughs cover both basic and advanced tasks, including creating projects, writing code in JupyterLab, managing environments, and publishing to a Git server.

Quickstarts are designed to help you quickly become familiar with the AI Workbench **desktop application**, **command line interface (CLI)**, and **NVIDIA-created example projects**. You can complete them in any order.

## Quickstart Guides

- [Basic Quickstart](/ai-workbench/quickstart/quickstart-basic) - Learn the core workflow: create a project, write code in JupyterLab, and push changes to Git.
- [Basic Quickstart (CLI)](/ai-workbench/quickstart/quickstart-cli) - Use the AI Workbench command line interface (CLI) to manage projects, environments, and containers.
- [Walkthrough: Project Dashboard for Onboarding, Monitoring and Managing Your Project](/ai-workbench/quickstart/quickstart-dashboards) - Use the **Project Dashboard** to monitor GPU usage, track project changes, and manage running applications.
- [Walkthrough: Customize Your Environment](/ai-workbench/quickstart/quickstart-environment) - Modify project environments, install dependencies, and configure resource settings.
- [Walkthrough: Customize Your Environment (CLI)](/ai-workbench/quickstart/quickstart-environment-cli) - Manage project environments using the CLI, including package installation and container customization.
- [Walkthrough: Add a Custom Application](/ai-workbench/quickstart/quickstart-custom-app) - Add and configure custom applications inside your AI Workbench project.
- [Advanced Walkthrough: Hybrid RAG](/ai-workbench/quickstart/quickstart-hybrid-rag) - Set up and run the Hybrid RAG example project, showcasing retrieval-augmented generation workflows.
- [Advanced Walkthrough: Use Your Own Container](/ai-workbench/quickstart/quickstart-byoc) - Bring your own container (BYOC) and integrate it into an AI Workbench project.
- [Install Claude Code in a Project Container](/ai-workbench/quickstart/quickstart-claude-install) - Install Claude Code in a project container.
- [Configure Claude Code Sandboxing in a Project Container](/ai-workbench/quickstart/quickstart-claude-sandbox) - Create a sandbox configuration repository for Claude Code.

## Next Steps

- Start with [Basic Quickstart](/ai-workbench/quickstart/quickstart-basic) to familiarize yourself with the workflow.
- If you prefer the command line, go to [Basic Quickstart (CLI)](/ai-workbench/quickstart/quickstart-cli).
- Learn how to customize environments in [Walkthrough: Customize Your Environment](/ai-workbench/quickstart/quickstart-environment) or [Walkthrough: Customize Your Environment (CLI)](/ai-workbench/quickstart/quickstart-environment-cli).
- Explore **NVIDIA-created example projects** like [Advanced Walkthrough: Hybrid RAG](/ai-workbench/quickstart/quickstart-hybrid-rag).
- For additional support, visit the [NVIDIA Developer Forum](https://forums.developer.nvidia.com/c/ai-data-science/nvidia-ai-workbench/671).