Affordances and Constraints of Automation and Augmentation
Qingyu Liang, Juanqiong Gou, Zhe Wang, Marina Dabić
Abstract
Human-AI collaboration is becoming increasingly prevalent in workplaces, and is considered to be an important model for the future of work. Consequently, AI is no longer seen merely as a tool but as a teammate working alongside humans. Currently, the design of AI in team collaboration, particularly human-AI collaboration patterns, has become a focal point for organizations. However, users' perceptions of the affordances and constraints of different collaboration patterns remain insufficient. Therefore, this study introduces a human-AI collaboration business simulation platform, used to simulate a future work environment that has two distinct human-AI collaboration patterns: automation and augmentation. In the unique context of the case enterprise platform, we further investigated the impact of task types (structured and unstructured tasks) on people's perceptions of automation and the influence of knowledge sources (AI designers' and end-users' knowledge-driven development) on people's perceptions of augmentation.