"It Felt a Bit Eerie": Exploring Humanlike Interactions During Collaborative Writing with an Artificial Agent

2026-05-23

AI Summary

This study investigates the impact of anthropomorphic interaction design on social connectedness and collaborative experience in human–AI teamwork. By developing three AI-assisted text editors with incrementally increasing levels of anthropomorphism—from asynchronous with no cursor to synchronous with a visible cursor—and conducting a user study with 48 participants, the research systematically examines how temporal synchrony and visual cues influence collaborative writing. Findings reveal that while synchronous suggestions enhance efficiency, they often lead to contextual misalignment; similarly, visualizing the AI’s cursor aids intention understanding but can evoke feelings of being monitored and discomfort. This work is the first to uncover the social costs and ethical risks inherent in anthropomorphic design within AI collaboration, offering empirical insights and ethical guidance for the development of human–AI cooperative systems.

Abstract

While human-AI collaboration systems have increasingly been built to increase efficiency or support creativity, little work has examined how the design of interactions shapes the social connection between human and artificial agent. We examine how the temporal and visual dimensions of collaboration shape the experience of a writing task. Specifically, we built three variants of an AI-assisted text editor along a spectrum of simulated humanlike interaction (synchronous and with a cursor) to machinelike interaction (asynchronous and without a cursor), and conducted a comparative user study (n=48). Our exploratory findings suggest that synchronous suggestions increased efficiency but led to contextual misalignment, while a visual cursor increased intent understanding but evoked feelings of surveillance. Taken together, humanlike design of artificial agents can create positive social expectations but also elicit social costs, especially without the alignment present in human-human collaboration. We extend our findings into design implications and ethical considerations when building human-AI collaboration systems.

Problem

• human-AI collaboration
• social connection
• humanlike interaction
• collaborative writing
• interaction design

Innovation

• humanlike interaction
• collaborative writing
• AI agent design
• social connection
• temporal and visual dimensions