@arizeai/phoenix-mcp

# Agent Cookbooks ### Tracing and Evaluating Agents <table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Agent Cookbook</strong></td><td>Build a customer support agent to trace activity, assess performance, and experiment with prompts and models.</td><td><a href=".gitbook/assets/app_llm.avif">app_llm.avif</a></td><td><a href="datasets-and-experiments/experiment-with-a-customer-support-agent.md">experiment-with-a-customer-support-agent.md</a></td></tr><tr><td><strong>Evaluate an Agent</strong></td><td>Trace and evaluate a "talk-to-your-data" agent. Includes evaluations for function calling accuracy, SQL query generation, code generation, and agent execution path.</td><td><a href=".gitbook/assets/agent-traces.png">agent-traces.png</a></td><td><a href="evaluation/evaluate-an-agent.md">evaluate-an-agent.md</a></td></tr><tr><td><strong>OpenAI Agents SDK Cookbook</strong></td><td>Create an agent with the OpenAI Agents SDK, trace its activity, benchmark with datasets, run experiments, and evaluate traces in production.</td><td><a href=".gitbook/assets/image.avif">image.avif</a></td><td><a href="evaluation/openai-agents-sdk-cookbook.md">openai-agents-sdk-cookbook.md</a></td></tr><tr><td><strong>Using Ragas to Evaluate a Math Problem-Solving Agent</strong></td><td>Create an agent using the OpenAI Agents SDK, trace its interactions, and evaluate performance using Ragas.</td><td><a href=".gitbook/assets/Ragas.jpg">Ragas.jpg</a></td><td><a href="evaluation/using-ragas-to-evaluate-a-math-problem-solving-agent.md">using-ragas-to-evaluate-a-math-problem-solving-agent.md</a></td></tr><tr><td><strong>Tracing and Evaluating a LangChain OpenAI Agent</strong></td><td>Build your own LangChain OpenAI agent using the function-calling API and inspect the agent's internals—all in a minimal setup with conversation and tool use.</td><td><a href=".gitbook/assets/image (2).avif">image (2).avif</a></td><td><a href="https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/langchain_agent_tracing_tutorial.ipynb">https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/langchain_agent_tracing_tutorial.ipynb</a></td></tr><tr><td><strong>Tracing and Evaluating a LlamaIndex OpenAI Agent</strong></td><td>Use the function-calling API to create a LlamaIndex OpenAI agent capable of conversation and tool use, and explore its behavior with Phoenix.</td><td><a href=".gitbook/assets/image (1).avif">image (1).avif</a></td><td><a href="https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/llama_index_openai_agent_tracing_tutorial.ipynb">https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/llama_index_openai_agent_tracing_tutorial.ipynb</a></td></tr></tbody></table>