Make it easy to dismiss or ignore undesired AI system services.
Engage in disambiguation or gracefully degrade the AI system’s services when uncertain about a user’s goals.
Enable the user to access an explanation of why the AI system behaved as it did.
Maintain short-term memory and allow the user to make efficient references to that memory.
Limit disruptive changes when updating and adapting the AI system’s behaviors.
Allow the user to globally customize what the AI system monitors and how it behaves.