New Framework Defines 8 UX Principles for AI Agents in the Workplace

As AI agents increasingly power enterprise workflows, a critical gap has emerged: there are no standard user experience (UX) guidelines for how humans should interact with these autonomous systems. In a new paper published on arXiv, researchers Kathrin Paimann, Elizangela Valarini, and Sebastian Juhl tackle this head-on by proposing a framework of eight core UX principles specifically for human-AI agent interaction in the workplace. The study, set to appear in the proceedings of Mensch und Computer 2026, combines five distinct research methods—a participatory design workshop, paper-and-pencil studies, expert review, meta-analysis, and in-depth interviews—to identify and validate these principles.

The framework provides actionable guardrails for software engineers and UX designers, ensuring that AI agents are not just powerful but also trustworthy and intuitive. Each principle comes with underlying criteria that can be directly applied during development. The authors emphasize that this is not a one-size-fits-all checklist but a structured foundation for future empirical studies on agentic AI in enterprise settings. By grounding the principles in rigorous methodology, the framework aims to bridge the gap between technical capability and human-centered design.

For professionals deploying AI agents—from customer support bots to autonomous code reviewers—this research offers a critical tool to avoid common pitfalls like opaque decision-making or lack of user control. The eight principles cover areas such as transparency, feedback, error recovery, and adaptability, all tailored to the unique challenges of AI agents that can act autonomously. The paper is a timely contribution as companies race to integrate AI agents into their operations, reminding us that good UX is the linchpin of successful adoption.