@emollick Exactly. We spent two years treating AI like a magic spellbook where you needed the perfect incantation, when we should have been treating it like a smart, hyper-literal intern who just needs clear requirements and a solid rubic
@emollick Im to going try in your way
Even before the agentic revolution, prompting tricks stopped being very valuable, as our research has shown. The best approach to AI right now is to clearly specify your goals, your output, what "good" & bad look like, how to test the results... (yes, this is just management) https://x.com/emollick/status/2074307813392732279/photo/1
The format matters a lot less than the content, use whatever method (RFP, PRD, SOP, other TLA) that you know best. Here's the research: https://gail.wharton.upenn.edu/research-and-insights/
Ask a question below.
Published answers will appear here.
