Eval Rubric Prompt
Builds a scoring rubric a grader model can apply consistently.
/ quick answer
Use to define model-graded scoring for a subjective AI output. Builds a scoring rubric a grader model can apply consistently.
Create an evaluation rubric for the AI output described below. Return:
1. DIMENSIONS — 3–5 scoring dimensions, each with a one-line definition.
2. SCALE — a 1–5 scale per dimension with concrete descriptions of what each score looks like.
3. AUTOMATIC FAILURES — conditions that force a score of 1 regardless of other qualities.
4. GRADER PROMPT — a ready-to-use prompt that scores one output against this rubric and returns JSON.
5. THRESHOLD — the pass score, with reasoning.
Be concrete enough that two different graders would agree.
Output type: {{OUTPUT_TYPE}}
User goal: {{GOAL}}
Non-negotiables: {{REQUIREMENTS}}1. DIMENSIONS — Accuracy: every claim is supported by the source. Completeness: answers all parts of the question...
What does the Eval Rubric Prompt prompt do?
Use to define model-graded scoring for a subjective AI output.
Which AI models work with this prompt?
It is model-agnostic: it works with any capable general model. Replace the bracketed variables with your own context before running it.
What output should I expect?
1. DIMENSIONS — Accuracy: every claim is supported by the source. Completeness: answers all parts of the question...
/ continue exploring
Related concepts
The vocabulary this page depends on.
- →AI Evaluation
AI evaluation is the measurement layer of an AI system: a fixed set of cases, a scoring method and a tracked pass rate you can regress against.
- →AI Monitoring
AI monitoring is production observability for model-driven systems: traces, cost, latency, tool failures and output-quality drift.
Related workflows
Turn this into a repeatable process.
- →Build an Eval Suite Before Optimising Prompts
Stop guessing whether a change improved anything.
- →Monitor an AI System in Production
See quality, cost and failure drift before your users report it.
Related tool stacks
The tools that run it in production.
- →AI Observability Stack
Traces, cost, evals and quality drift for AI systems in production.
Related prompts
Reusable prompts for this job.
- →AI System Threat Model Prompt
Produces a concrete threat model for an AI system with tool access.
- →AI Code Review Rubric Prompt
A reviewer prompt that finds real defects instead of style opinions.
- →Prompt Improver Prompt
Iterate a weak prompt into a strong one using best practices.
- →Strategic Analyst Prompt
Turn a business situation into a McKinsey-style strategic memo.
Comparisons & alternatives
Pick between the options.
- →Model-Graded Evals vs Assertion Evals
Assertions are cheap, fast and objective; model grading captures quality you cannot express as a rule.