langfuse-agent-eval

What problem does it solve?

This Skill streamlines the process of evaluating AI agent performance by automating experiment execution, failure analysis, and documentation of findings.

Core Features & Use Cases

• Automated Experimentation: Runs evaluation cycles using Langfuse experiments.
• Failure Analysis: Groups and analyzes agent failures to identify root causes.
• Recommendation Generation: Provides specific, actionable recommendations for improvement.
• Use Case: Improve the accuracy and reliability of a customer support agent by running an evaluation cycle, identifying common failure patterns, and implementing targeted fixes.

Quick Start

Use the langfuse agent eval skill to run an evaluation cycle for the 'customer-support-agent'.