The perfect prompt doesn't instruct the model on what it already knows how to do.
TL;DR: Reasoning models already verify and pace themselves, so drop those prompts and set real effort, scope, length, autonomy.
Common Mistake ❌
You still write prompts for a model that evolved and stopped needing them.
"Double-check your work," "think step by step," "be concise," and a wall of REQUIRED/MANDATORY rules get pasted into every request, the same gratuitous context you'd flag in a variable name, on the assumption that more instruction always buys better output, as if the model just needed one more all-caps reminder to remember how to think.
