A data pipeline requires Claude to always output valid JSON with a specific schema. During production, the team observes occasional schema violations (missing fields, wrong types) that break downstream parsing. Which combination of techniques most reliably enforces schema compliance?

A is correct because schema compliance requires a defense-in-depth approach: the system prompt establishes the requirement, the explicit schema prevents ambiguity about field names and types, few-shot examples demonstrate correct structure, and post-generation validation with retry handles edge cases where the model still deviates (which happens at low rates even with good prompting). B is wrong because a simple instruction to output JSON is insufficient — without schema specification, Claude may include extra fields, omit optional-seeming required fields, or use inconsistent types. C is wrong because JSON linting fixes syntax errors (malformed JSON) but cannot add missing required fields or correct type mismatches — structural schema violations require model regeneration, not string manipulation. D is wrong because temperature 0 makes output deterministic for a given input, but it does not guarantee schema compliance — the model can deterministically produce non-compliant output if the prompt does not sufficiently constrain the structure.