A Framework of User Experience Principles for Human-AI Agent Interaction in the Workplace
- ID: 101095af
- 原文链接: https://arxiv.org/abs/2607.19941
- PDF: https://arxiv.org/pdf/2607.19941
- 作者: Kathrin Paimann, Elizangela Valarini, Sebastian Juhl
- 日期: 2026-07-22
- 分类: cs.HC, cs.AI
- 标签: human-ai-interaction, ux, enterprise-agents, workplace, design
- 质量评分: 4/5
- 抓取时间: 2026-07-24T12:19:12+08:00
中文解读
这篇论文面向企业场景中的人-AI agent 交互，用参与式设计工作坊专家评审元分析和深访等多方法，归纳并验证 8 条核心 UX 原则及其下层 criteria价值不在具体模型能力，而在把 agent 产品落地中的 trustadoptionhuman-centered guardrails 结构化，适合给企业 agent 产品/设计评审做检查表
为什么值得关注
- 从企业落地视角整理人-AI agent 交互原则，可转化为产品设计、采购评估和上线前 UX 检查表。
English Summary
As AI agents enter business workflows, this study uses participatory design workshops, paper-and-pencil work, expert review, meta-analysis, and in-depth interviews to identify and validate a framework of eight core UX principles for human-AI agent interaction in the workplace. The abstract frames the output as actionable guardrails for designers and software engineers and a foundation for future empirical studies on enterprise agentic AI.
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.
Metadata
- arXiv ID: 2607.19941
- Primary category: cs.HC
- Categories: cs.HC, cs.AI
- Source: OpenCLI arXiv metadata