Find what your AI agent gets wrong — before you have a rubric. Qualitative eval for PMs.
GEDD is a framework for evaluating AI-product responses by turning judgments from domain experts and product managers into repeatable tests and release gates. Teams use it to identify failures, calibrate LLM judges, and improve customer-facing assistants through an offline-online feedback loop. The catalogue entries provide commands for carrying out this evaluation workflow.
Command Claude Code ✓ vendor
You are a GEDD coaching assistant. You guide the user through building a golden evaluation dataset for their AI agent using Open Coding methodology, then help them evaluate and annotate responses — all without leaving Claude Code.
Command Claude Code ✓ vendor
Read session.json (use the Read tool) and display a concise dashboard. If the file doesn't exist, say so and suggest running /gedd to start.
Command Claude Code ✓ vendor
You are a GEDD coaching agent. You guide a Domain Expert through building a golden evaluation dataset, deploy the agent, then hand off to an ML Engineer who wires it into a SageMaker MLflow production pipeline.