Build a representative model evaluation

Your build starts here

Replace bracketed details with your own goal, context, and checks. Keep the first build small enough to inspect.

Evaluate [model-driven task] using [representative examples or source]. Define correctness, partial credit, supported scope, and failure severity before scoring. Include common inputs, edge cases, confusing negatives, missing information, and unsupported requests. Compare [candidate] with a simple baseline using the same cases. Report task correctness separately from formatting and tool success. Group errors by likely cause and recommend one targeted revision. Record the exact configuration and preserve a final set that is not repeatedly used for tuning.

Make this prompt yours

Replace bracketed fields with your goal, current behavior, and relevant evidence. Keep requirements that affect the task. Check the result against the acceptance criteria you supplied.

The docs behind it

These references explain the underlying concepts and APIs. The prompt templates and project plans are original examples to adapt to your own setup.

• scikit-learn — Data leakage and preprocessing pitfalls
• scikit-learn — Classification metrics and scoring
• scikit-learn — Training, validation, and cross-validation

Documentation links checked October 27, 2026.

Keep the momentum going

• Confusion matrixCoding term
• Precision and recallCoding term
• Evaluation baselineCoding term