Skill UI

This tool allows users to systematically evaluate and rank the outputs of multiple agents within an AgentHub session. It supports metric-based evaluation (running custom commands for measurable metrics like speed or resource usage), or an advanced LLM Judge Mode. The LLM Judge compares results based on criteria like correctness, simplicity, and overall quality, helping users determine the best-performing agent for the task.

This skill guides users on setting up and running LLM-as-judge evaluations using Arize. It covers defining evaluators (including prompts, classification choices, and models) and executing tasks against real data spans or experiments. It supports key metrics like hallucination, faithfulness, and correctness, and facilitates continuous monitoring for comprehensive LLM performance analysis.