It's Not How Much AI, It's How Well: A Practical Spectrum for Advanced AI Use(zachwills.net)
zachwills.net
It's Not How Much AI, It's How Well: A Practical Spectrum for Advanced AI Use
https://zachwills.net/its-not-how-much-ai-its-how-well-a-practical-spectrum-for-advanced-ai-use/
This framework makes a lot of sense. I think the general approach of eschewing one-shot prompts in favor of letting the LLM craft its own prompts (per your standards) is the missing piece in a lot of workflows.