Adapting AI to the Moment: Understanding the Dynamics of Parent-AI Collaboration Modes in Real-Time Conversations with Children

TL;DR

This paper explores how parents and AI systems dynamically collaborate during real-time conversations with children, emphasizing adaptable modes and strategies to improve support in sensitive, evolving interactions.

Contribution

It introduces COMPASS, a flexible research tool, and uncovers how collaboration modes and parental strategies evolve in real-time, informing better design of adaptive support systems.

Findings

Parent-AI collaboration involves evolving modes that adapt to context.

Three parental strategies influence engagement with AI.

Findings inform design of flexible, context-aware parental support systems.

Abstract

Parent-AI collaboration to support real-time conversations with children is challenging due to the sensitivity and open-ended nature of such interactions. Existing systems often simplify collaboration into static modes, providing limited support for adapting AI to continuously evolving conversational contexts. To address this gap, we systematically investigate the dynamics of parent-AI collaboration modes in real-time conversations with children. We conducted a co-design study with eight parents and developed COMPASS, a research probe that enables flexible combinations of parental support functions during conversations. Using COMPASS, we conducted a lab-based study with 21 parent-child pairs. We show that parent-AI collaboration unfolds through evolving modes that adapt systematically to contextual factors. We further identify three types of parental strategies--parent-oriented, child-oriented, and relationship-oriented--that shape how parents engage with AI. These findings advance the understanding of dynamic human-AI collaboration in relational, high-stakes settings and inform the design of flexible, context-adaptive parental support systems.