Enacting Constructive Conflicts with AI Agents to Enhance Reconsideration among Novice Interaction Designers

2026-08-04

AI Summary

This study addresses a common challenge faced by novice interaction designers—difficulty in deeply refining design proposals due to overlooking conflicting stakeholder perspectives. To tackle this, the work introduces a novel approach that integrates adversarial design theory into generative AI agents, which proactively simulate diverse dissenting viewpoints to instigate constructive conflict and thereby stimulate designers’ critical reflection and iterative improvement. Through a human–AI interaction experiment comparing three conditions—self-reflection, step-by-step guidance, and AI-mediated interaction—the results demonstrate that the proposed agent significantly enhances the depth of designers’ reconsideration, increases the number of design improvements, and fosters greater creative ideation and iteration compared to alternative methods. This research establishes a new paradigm for leveraging AI to support reflective design practice.

Abstract

Generative AI agents are increasingly used in interaction design to facilitate ideation and offer critique, often following their own internal reasoning. These interactions tend to add design ideas and expand the design space. Our work explores an antagonistic role for design agents, prompting designers to engage with stakeholder tension. We built an AI agent inspired by adversarial design theory that enacts constructive conflict. We examine the agent's influence in a between-subjects experiment with 45 design students across three conditions: Self Reflection (unsupported review of the design proposal), Stepwise Guidance (written prompts that walk designers through a constructive-conflict framework), and Interactive Engagement (an AI agent that enacts the constructive-conflict framework interactively by synthesizing stakeholder pushback). The latter two conditions share the framework but differ in whether it is self-enacted or agent-enacted. Results show that, compared with Self Reflection, both the Stepwise Guidance and Interactive Engagement groups reported significantly higher self-reconsideration and made more improvements to their design proposals. Compared with Stepwise Guidance, the antagonistic agent introduced more conflictual perspectives, and participants in the Interactive Engagement condition generated and discarded more ideas. These findings suggest that agent-enacted constructive conflict can turn reconsideration into concrete design actions and deepen engagement with divergent stakeholder perspectives.

Problem

• constructive conflict
• reconsideration
• interaction design
• adversarial design
• stakeholder tension

Innovation

• constructive conflict
• adversarial AI agent
• stakeholder tension
• design reconsideration
• interactive engagement