A Framework of User Experience Principles for Human-AI Agent Interaction in the Workplace

ABSTRACT As AI agents become integral to business workflows, establishing guiding user experience (UX) principles is crucial for ensuring user trust and successful adoption. To address this, our study uses a multi-method approach—combining participatory design workshop, paper-and-pencil, expert review, meta-analysis, and in-depth interviews—to identify and validate a design framework of eight core UX principles for human-AI agent interaction in the workplace. Together with their underlying criteria, these principles provide actionable guardrails for designers and software engineers, creating a foundation for developing effective and human-centered AI agent interactions. This study contributes to a structured foundation for future empirical studies on agentic AI in enterprise settings.

Introduction. AI agents are emerging as a fundamental element of the modern business landscape. They are autonomous software systems that define objectives, execute multi-step plans, make decisions, interpret their operational environment, and engage with human users through natural language interaction (Bandi et al. 2025). Agentic systems are occupying organizational roles previously held exclusively by humans (Calvanese et al. 2026; Borghoff et al. 2025). This shift fundamentally alters the conditions under which business users engage with software and the experience they expect from them. Traditional user experience (UX) practices, developed for non-agentic systems producing predictable, human-controlled outcomes, prove insufficient to account for the complexity introduced by autonomous and adaptive AI agents. A growing body of literature addresses UX design for human interaction with AI systems, identifying criteria such as controllability, explainability, ethics, privacy, transparency, and collaboration as core design requirements (Xu 2026; Li et al. 2026; Xu 2024; Diederich et al. 2022).

Discussion / Conclusion. This study contributes to the HCI and HCAI literature by providing an empirically grounded, enterprise-focused foundation for designing human-AI agent interactions. Through a rigorous multi-method approach, we identified and systematized eight core UX principles with actionable underlying criteria and derived a design framework to narrow the critical gap between rapidly advancing agentic AI capabilities and their adaptation in organizational contexts. Our framework addresses a fundamental challenge facing enterprises today: how to integrate AI agents into workflows while maintaining meaningful human oversight, fostering user trust, and adhering to organizational governance requirements. Our results show that business users prioritize principles centered on human control, reliability, context-awareness, and safety. These are not merely theoretical ideals but practical necessities that directly shape user acceptance and effective collaboration with AI agents. Furthermore, the underlying criteria derived here provide concrete, implementable guidance for UX designers and software engineers.