Examining Autocompletion as a Basic Concept for Interaction with Generative AI

TL;DR

This paper explores autocompletion as a fundamental interaction concept in human-AI interfaces, analyzing its elements across domains and discussing its role in designing interactions with generative AI.

Contribution

It offers a conceptual framework for understanding autocompletion's role in human-AI interaction, extending its application beyond search to generative AI systems.

Findings

Autocompletion elements are common across multiple application domains.

Autocompletion enhances user input extension and completion in AI interactions.

The paper provides a conceptual lens for designing human-AI interfaces.

Abstract

Autocompletion is an approach that extends and continues partial user input. We propose to interpret autocompletion as a basic interaction concept in human-AI interaction. We first describe the concept of autocompletion and dissect its user interface and interaction elements, using the well-established textual autocompletion in search engines as an example. We then highlight how these elements reoccur in other application domains, such as code completion, GUI sketching, and layouting. This comparison and transfer highlights an inherent role of such intelligent systems to extend and complete user input, in particular useful for designing interactions with and for generative AI. We reflect on and discuss our conceptual analysis of autocompletion to provide inspiration and a conceptual lens on current challenges in designing for human-AI interaction.