Free Your LLM to Pursue Goals, Not Follow Rules
How to choreograph LLM behavior with schema-shot prompts
Written by
Exploring the intersection of design and promptcraft
A design leader and product builder exploring the intersection of design and AI. I experiment with local models and systems thinking to understand how these tools behave, break, and become useful. Favorite LLMs: Claude, ChatGPT, Qwen 3.6 27b & 35B A3B, Gemma4 31b, and a constant daily experimental driver.
Responses
Markdown supported · ⌘↵ to post
AlteredOxide
I like this approach and will certainly give it a try. Thanks for sharing!