mlflow-evaluation

What problem does it solve?

This Skill helps you rigorously evaluate the quality, safety, and performance of your Generative AI agents and LLM applications, ensuring they meet your project's standards before deployment.

Core Features & Use Cases

• Automated Evaluation: Run evaluations using built-in or custom scorers.
• Trace Analysis: Debug agent behavior by analyzing execution traces.
• Production Monitoring: Set up continuous quality checks on live traffic.
• Use Case: You've built a customer support chatbot. Use this Skill to automatically evaluate its responses for safety, accuracy against expected answers, and adherence to brand guidelines, then monitor its performance in production.

Quick Start

Use the mlflow-evaluation skill to evaluate your agent using the provided test dataset and safety and guidelines scorers.