engineering-prompts-and-outputlisted

# Engineering Prompts and Output ## Overview Best-practice reference for the prompt-and-output layer: explicit criteria in system prompts, few-shot construction, schema-enforced output, validation/retry, batch processing, and review pipelines. Each reference module states the correct pattern, the named anti-patterns, and ends with an **Audit Checklist** of verifiable conditions. ## When to use - Writing or reviewing a system prompt, few-shot set, output schema, or an automated review pipeline - Debugging: inconsistent verdicts, invalid JSON, false-positive floods, hallucinated values, missed defects on self-review - Deciding: severity criteria vs confidence filtering, `tool_choice` mode for extraction, retry strategy, batch vs real-time Not for tool interface design itself (use designing-tools-and-mcp) or human-review calibration (use managing-context-reliability). ## Quick reference | Module | Read when the question is about | |---|---| | `references/4-1-system-prompts-with-explicit-criteria.md` | Explicit severity criteria, the false-positive trust problem | | `references/4-2-few-shot-prompting.md` | Constructing examples, hallucination reduction, false-positive control | | `references/4-3-structured-output-with-tool-use.md` | The three `tool_choice` modes, what `tool_use` does not guarantee, schema design | | `references/4-4-validation-retry-and-feedback-loops.md` | Retry-with-error-feedback, its limits, schema vs semantic errors | | `references/4-5-batch-processing