Prompt Specificity & Precision

Core

Design prompts with explicit criteria to improve precision and reduce false positives · Difficulty 2/5

specificitycriteriaprompting

Vague prompts produce inconsistent results. Prompt specificity means replacing ambiguous instructions with precise criteria that the model can apply deterministically.

Example: Comment Analysis

Vague: "Check that comments are accurate and up-to-date"

Flags TODOs, descriptive comments (false positives)

Misses genuinely outdated comments (false negatives)

Specific: "Flag comments only when their claimed behavior contradicts actual code behavior"

Eliminates false positives on acceptable patterns

Catches genuinely misleading comments

Principles

Define criteria, not goals: "Flag contradictions" not "check accuracy"

Specify boundaries: What should and should NOT be flagged

Use severity definitions: Concrete code examples for each severity level

Test with edge cases: Verify the criteria handle ambiguous inputs

Key Takeaways

✓Replace vague goals with specific, actionable criteria
✓Define what should NOT be flagged, not just what should
✓Concrete severity criteria with examples improve consistency

Related Concepts

Explicit Criteria over Vague Instructions

Replace vague goals with specific, categorical criteria the model can apply deterministically

Classification Consistency & False Positive Reduction

Use absolute criteria with concrete examples for each classification level

Test Yourself1 of 1

Your automated review analyzes comments and docstrings. The current prompt instructs Claude to "check that comments are accurate and up-to-date." Findings frequently flag acceptable patterns while missing comments that describe behavior the code no longer implements. What change addresses the root cause?