Prompt LibraryEngineering
Messy-to-Structured Output Normalizer Prompt
Turn inconsistent text into a clean JSON schema.
The prompt
Normalize the messy input below into the target JSON schema.
Rules:
- If a field is ambiguous in the input, set it to null and add a "warnings" array noting the ambiguity.
- If a field is present but empty, keep it as empty string/array, not null.
- Do not invent fields not in the schema.
- Dates must be ISO 8601; if unparseable, null + warning.
Schema:
{{schema}}
Input:
{{input}}Replace the {{fields}} with your own context and tighten the rules to match your domain.
More Engineering prompts
LLM Structured Output Contract & Validator Prompt
Pair a strict output schema with the exact validation code to enforce it.
LLM Observability & Tracing Schema Prompt
Define what to log for every model call so incidents are debuggable.
Streaming-Safe LLM Output Format Prompt
Structure output so it stays useful when streamed token by token.
