> ## Documentation Index
> Fetch the complete documentation index at: /docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Courses

> Learn Arize AX through video walkthroughs and self-paced courses on tracing, evaluation, and agents.

Learn Arize AX from the ground up. Explore video series and courses that teach the fundamentals of evals and AI observability, then build a complete path through the platform: instrument your application, observe its behavior, evaluate output quality, and improve it with confidence.

## Arize AX in 3 minutes

Start with a quick tour of what Arize AX does and how tracing, evaluation, and iteration fit together to help you ship AI applications you can trust.

[Learn Arize AX](https://www.youtube.com/embed/0_GMkTyTcDo)

***

## Go deeper

When you're ready to go deeper, explore our video series and courses:

> [card] [Getting started with Arize AX](/docs/ax/learn/courses/getting-started-with-ax/overview.md)
>
> A video series covering the full workflow end to end, from your first trace to improving a production agent.

> [card] [AI agent mastery](/docs/ax/learn/courses/ai-agent-mastery/overview.md)
>
> A deep dive on building, observing, evaluating, and improving production agents.

> [card] [Ship Real Agents: Hands-On Evals for Agentic Applications](/docs/ax/learn/courses/ship-real-agents-hands-on-evals.md)
>
> Trace an agent, diagnose failures, build evaluations, and use experiments to verify improvements.

> [card] [How to Write Your First AI Eval](/docs/ax/learn/courses/how-to-write-your-first-ai-eval.md)
>
> Learn to read traces, define pass or fail criteria, and build an LLM judge for an AI agent.

> [card] [Shipping AI That Works: An Evaluation Framework for PMs](/docs/ax/learn/courses/shipping-ai-that-works-evaluation-framework-for-pms.md)
>
> A practical evaluation framework for product managers working on LLM-powered products.

> [card] [Agents That Self Improve While You Sleep](/docs/ax/learn/courses/agents-that-self-improve-while-you-sleep.md)
>
> Build an improvement loop with tracing, Signal, evaluations, experiments, and human review.