[imglorp]

A 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.

[kvirani]

You're on to something here. Can we go more meta and define these dynamically such that users can customize multiple output streams?