phoenix-observability

What problem does it solve?

This Skill provides deep visibility into AI applications, enabling debugging, evaluation, and monitoring of LLM performance and behavior.

Core Features & Use Cases

• LLM Tracing: Visualize the entire lifecycle of LLM requests, including prompts, responses, and intermediate steps.
• Evaluation: Run systematic tests and quality assessments on your LLM outputs against datasets or references.
• Monitoring: Track key metrics and identify issues in production AI systems in real-time.
• Use Case: When your chatbot starts giving nonsensical answers, use Phoenix to trace the problematic conversation, identify where the LLM went wrong, and pinpoint the faulty prompt or context.

Quick Start

Launch the Phoenix observability UI by running phoenix serve in your terminal.