Autocompletion as a Basic Interaction Concept for User-Centered AI

Abstract

With this position paper we propose that autocompletion can be interpreted as a basic interaction concept in the interaction between humans and systems using artificial intelligence (AI). Autocompletion is well known from text input where the system predicts intended user input, e.g. in search engines. In our research on human-AI collaboration we observe parallels to such textual autocompletion but in different application contexts, such as text generation, mock-up generation, and layout solvers. We compare exemplary related work to highlight autocompletion as a reoccurring and reusable interaction concept. We discuss that identifying underlying interaction primitives in user-centered AI can help to inform concrete design solutions for interactions and user interfaces, and could be a starting point for future research in this area.