Also, downgrade LLM for commands to mini. It's much cheaper and I only upgraded because of the
interpretation complexities that the insight command introduced.
We are implementing a much better approach with Ask.
This is a workaround to make the prototype work. We create a context on the fly to execute AI-derived
commands. When those require listing cards, we ended up losing the notion of "being on a perma screen".
Jorge Manrubia