alt Hacker NewsA very minor porcelain on some of the agent input UX could present this structure for you. Instead of a single chat window, have four: task, context, constraints, output format.
And while we're at it, instead of wall-of-text, I also feel like outputs could be structured at least into thinking and content, maybe other sections.
You're on to something here. Can we go more meta and define these dynamically such that users can customize multiple output streams?