LLM Prompt Engineering for Structured Outputs: What I Stopped Doing

JSON mode and function calling replaced most of my prompt gymnastics. What I spent time optimizing before those features existed and what still requires careful prompting.

Overview

This note is part of the field-notes archive generated for this site. The summary below is the published excerpt; you can expand the full write-up anytime in the CMS.

Related notes

• Rag Vs Finetuning Decision Framework
• Quantization War Stories Llm

Tags

• llm
• prompt-engineering
• structured-outputs
• machine-learning
• api