When Should an AI Act? A Human-Centered Model of Scene, Context, and Behavior for Agentic AI Design
This work provides a foundational model and principles for designers of agentic AI systems to improve contextual sensitivity and judgment in AI interactions, addressing a core challenge in human-AI collaboration.
This paper proposes a conceptual model for agentic AI to determine when, why, and whether to act, addressing the issue of AI failing due to a lack of principled judgment. The model integrates Scene (observable situation), Context (user-constructed meaning), and Human Behavior Factors, and from this, five agent design principles are derived to guide intervention depth, timing, intensity, and restraint.
Agentic AI increasingly intervenes proactively by inferring users' situations from contextual data yet often fails for lack of principled judgment about when, why, and whether to act. We address this gap by proposing a conceptual model that reframes behavior as an interpretive outcome integrating Scene (observable situation), Context (user-constructed meaning), and Human Behavior Factors (determinants shaping behavioral likelihood). Grounded in multidisciplinary perspectives across the humanities, social sciences, HCI, and engineering, the model separates what is observable from what is meaningful to the user and explains how the same scene can yield different behavioral meanings and outcomes. To translate this lens into design action, we derive five agent design principles (behavioral alignment, contextual sensitivity, temporal appropriateness, motivational calibration, and agency preservation) that guide intervention depth, timing, intensity, and restraint. Together, the model and principles provide a foundation for designing agentic AI systems that act with contextual sensitivity and judgment in interactions.