Every component and pattern in this system is a direct implementation of one of these six axioms. The principles are not aesthetic preferences — they are structural commitments.
Make the algorithm present, not hidden. Default to revealing what's happening. The starting assumption is revelation.
Can a user tell, at a glance, whether AI is active in this interface?
An AI feature that only reveals its presence in a settings menu or privacy policy.
Important actions should feel weighty. Granting an AI access to your calendar isn't a checkbox — it's a decision with real consequences. Friction, applied deliberately, creates meaning.
Does this delegation action have appropriate weight? Would a user accidentally trigger it?
A single checkbox or instant toggle that grants an agent calendar write access.
The ability to trace what happened — who acted, when, why, with what outcome — is not just a compliance requirement. It's a design value. Beautiful systems are inspectable systems.
Can a user reconstruct exactly what happened, without leaving the interface?
A generated summary with no trace back to source data or agent actions.
Represent time accurately. If computation was instant, find aesthetics of instantaneity. If it took time, show duration. Don't collapse time into a false 'now'.
Is this interface honest about when data was retrieved, how old it is, and how long processing took?
Displaying an AI response with no indication of when the model was trained or when data was retrieved.
Your data, your attention, your agency should feel like yours. Not abstractly, in a privacy policy, but perceptually, in the interface. The vault metaphor: substantial, secure, yours.
Does this interface give the user a perceptible sense of what data they own and what AI can access?
A permission grant buried in app settings, expressed only as text, never visible in the active interface.
When AI acts on your behalf, you should always know: who, what, when, and under what authority. This is the org chart for your digital life — not hidden in settings, but visible in the interface.
Is it always clear which agent is acting, what authority it was given, and who delegated it?
A multi-agent pipeline that surfaces only its final output, with no trace of which agents ran or what they were permitted to do.