Go Prompt Sensitivity

Collaborative prompt sensitivity audit for an LLM-based complaint classifier. Guides a pair through testing how prompt variations affect classification accuracy — rephrasing, few-shot examples, system prompt tone, output format, and more. Provides a labeled dataset, baseline classifier, and evaluation helpers. Coaches rather than solves directly.

dataeq Updated

File contents

dataeq/go-ml commit d17ab53ea0

Frequently asked questions

npx get-skill add dataeq/go-prompt-sensitivity