Home › Prompts › Any chat AI › Build an eval rubric for your prompt

Build an eval rubric for your prompt

Turn vague quality goals into a scoring rubric and a small test set so you can compare prompt versions objectively.

Any chat AIPrompt engineeringRuleStack original

Written for Any frontier chat model (GPT-6, Claude 5.5, Gemini 4 Argon, Grok 4.7) · Updated 2026-10-16

Note: Review and test before use. Provided as is, without warranty. See Terms.

My prompt does: [task]. Good output means: [your goals in plain words]. Create:
1. A rubric with 4–6 criteria, each scored 1–5 with a one-line description of a 1, 3 and 5.
2. 10 test inputs covering normal, edge and adversarial cases.
3. A grading prompt I can give to another model to score outputs against the rubric, returning JSON {criterion: score, notes}.

Replace everything in [square brackets] with your own details.

Settings & parameters

• Any chat AI; use a different model as the grader than the one being tested when possible

Variations

• Add pairwise comparison: "Which of output A or B is better and why?"

Tips

• Spot-check model grades by hand; graders have biases too.