Time when to act or interrupt based on the user’s current task and environment.
Ensure the AI system’s language and behaviors do not reinforce undesirable and unfair stereotypes and biases.
Engage in disambiguation or gracefully degrade the AI system’s services when uncertain about a user’s goals.
Immediately update or convey how user actions will impact future behaviors of the AI system.
Inform the user when the AI system adds or updates its capabilities.
