OpenAI published a new prompting guide for GPT-5.6 Sol, its newly released flagship model, advising users to stop writing multi-page system prompts. The core idea is outcome-first prompting: define what good looks like, set the stopping conditions, and get out of the way. OpenAI backs this with numbers: In internal coding agent tests, leaner system prompts improved evaluation scores by roughly 10–15% while cutting total tokens by 41–66% and costs by 33–67%. The guide introduces a first-ever section on Programmatic Tool Calling and highlights the text.verbosity API parameter—both absent from the GPT-5 playbook. The guide warns that GPT-5.6 follows prompt contracts closely, and that "conflicting rules can create more instability than missing detail." OpenAI heavily advises against using the old trick of resorting to absolutes like “always do this” or “never do that” to steer the AI’s behavior in a specific direction.