When Should an AI Act? A Human-Centered Model of Scene, Context, and Behavior for Agentic AI Design

TL;DR

This paper introduces a human-centered model for agentic AI that integrates scene, context, and behavior to improve the timing and appropriateness of AI interventions, grounded in multidisciplinary insights.

Contribution

It presents a novel conceptual model and five design principles to guide the development of contextually sensitive and judicious agentic AI systems.

Findings

Model explains how scenes can have different behavioral meanings

Five design principles for agentic AI intervention

Grounded in multidisciplinary perspectives

Abstract

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.