Skip to content

Prompt engineering checklist

A pre-flight checklist before shipping a new agent prompt to production.

Before shipping a prompt

  • Output format is explicitly specified (schema, not prose description)
  • Hard constraints are stated immediately before the task, not buried earlier
  • At least 3 edge cases have been manually tested
  • The prompt is version-controlled with a changelog entry
  • There’s a fallback behavior defined for malformed output
  • Token budget is accounted for (input + expected output)

Common failure patterns

SymptomLikely cause
Inconsistent output structureFormat described in prose, not enforced
Ignores late instructionsConstraints buried too early in a long prompt
Overly verbose reviewer feedbackNo concrete rubric given
Silent truncationOutput budget not reserved separately from input