Verified record · from the answer index

write-judge-prompt

Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with

skill:ai-evals-course/evals-skills/write-judge-prompt · published by ai-evals-course · source repository