Four words. That’s everything the model gets.
The request stays the same.
What surrounds it doesn’t.
Who is working: role, expertise, goals.
What “this” actually is: the project, the task, what matters now.
What kind of help fits: format, depth, style.
What is happening right now: momentum, friction, focus.
None of this is in the request. All of it decides whether the help is useful.
Flip what the AI knows. Watch the answer change.
Before each agent step, Qualia-1 runs a single pass over every candidate context unit — the structured context, plus the live work-state.
Everything that could go in the window flies in — tagged with where it came from and what kind of fact it is.
The units selected for this step, in priority order. Reconciled facts with provenance attached. Sized for the window’s budget — held-back items stay available for later steps.
depth — terse fix, or scaffolded explanation. format — bullet, paragraph, code, table. tools — which to expose, which to suppress. timing — surface now, queue, or defer.
You already felt this above: flipping work-state never changed the facts — it changed the directive.
Qualia-1 is how AI gets it — from the interaction itself.