Skip to main content

Getting started with Phoenix#

Not sure where to start? Try an end-to-end tutorial for a guided walkthrough of Phoenix’s core features. These tutorials cover tracing, evaluation, and experimentation:

Python Walkthrough
TypeScript Walkthrough

Discover workflows that illustrate how teams use Phoenix to build, evaluate, and scale AI systems.

Optimizing Coding Agent Prompts - Prompt Learning
Aligning LLM Evals with Human Feedback
Write your First Custom LLM Eval

Agent Demos#

These example agents are fully instrumented with OpenInference and utilize end-to-end tracing with Phoenix for comprehensive performance analysis. Enter your Phoenix and OpenAI keys to view traces.

Code Generation Agent

Explore a Code Generator Copilot Agent designed to generate, optimize, and validate code.

RAG Agent

Enter a source URL and collect traces in Phoenix to see how a RAG Agent can retrieve and generate accurate responses.

Computer Use Agent

Test out a Computer Use (Operator) Agent built to execute commands, edit files, and manage system operations.