phoenix-observability

Trace, evaluate, and monitor LLM applications with OpenTelemetry integration.

2|Updated Feb 4, 2026

Search Tags:#monitoring #evaluation #observability #phoenix #ai ops #llm tracing

Ready to run

npx skills add https://github.com/zhuangbiaowei/smart_bot --skill phoenix-observability-zhuangbiaowei

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: phoenix-observability
Source: https://github.com/zhuangbiaowei/smart_bot/tree/main/skills/phoenix
Command: npx skills add https://github.com/zhuangbiaowei/smart_bot --skill phoenix-observability-zhuangbiaowei

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires arize-phoenix, and includes references (resource) components.

What problem does it solve?

This Skill provides a comprehensive platform for observing, debugging, and evaluating Large Language Model (LLM) applications, enabling developers to understand and improve their AI systems.

Core Features & Use Cases

LLM Tracing: Visualize the execution flow of LLM calls with detailed spans and traces.
Evaluation: Run systematic evaluations on datasets to assess model performance.
Monitoring: Gain real-time insights into production AI systems.
Use Case: When debugging a complex LLM chatbot that is giving incorrect responses, use Phoenix to trace the exact sequence of LLM calls, context retrieval, and tool usage to pinpoint the source of the error.

Quick Start

Install the necessary libraries and launch the Phoenix server.

Frequently Asked Questions about phoenix-observability

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I debug LLM issues with tracing?▼

LLM tracing visualizes the execution flow of LLM calls with detailed spans to pinpoint errors. By tracing the exact sequence of context retrieval and tool usage, you can identify the source of incorrect responses in your AI systems.

What is the best way to monitor production AI systems?▼

Monitoring production AI systems requires gaining real-time insights into their operations to ensure stability. This approach allows developers to observe live behavior, track performance metrics, and maintain the reliability of deployed LLM applications.

How do I run systematic evaluations on LLM datasets?▼

Running systematic evaluations on datasets assesses LLM performance by analyzing model outputs against expected results. This process helps developers measure accuracy, identify weaknesses in context retrieval, and improve overall AI system quality.

Does Phoenix observability work with OpenTelemetry integration?▼

Yes, Phoenix observability supports OpenTelemetry integration for various LLM frameworks. This compatibility allows you to standardize tracing data collection and seamlessly monitor your existing LLM applications without extensive code modifications.

Do I need the arize-phoenix library to trace LLM applications?▼

Yes, you need to install the arize-phoenix library to enable AI observability for LLM tracing. This dependency is required to launch the server and start visualizing execution flows, running evaluations, and monitoring systems.

Can I visualize execution flow for complex LLM chatbots?▼

Yes, visualizing execution flow for complex LLM chatbots allows you to trace exact sequences of LLM calls. You can inspect detailed spans of context retrieval and tool usage to debug incorrect responses effectively.