Collaborative Document Editing with Multiple Users and AI Agents
This addresses the challenge of integrating AI into collaborative writing for teams, though it is incremental in adapting existing collaborative features.
The paper tackles the problem of AI writing tools being designed for individuals, which complicates collaboration by requiring co-writers to leave shared workspaces to use AI and then reintegrate results; it proposes integrating AI agents directly into collaborative writing environments, and a user study with 30 participants over one week showed that teams incorporated agents into existing norms of authorship, control, and coordination rather than treating them as team members.
Current AI writing support tools are largely designed for individuals, complicating collaboration when co-writers must leave the shared workspace to use AI and then communicate and reintegrate results. We propose integrating AI agents directly into collaborative writing environments. Our prototype makes AI use transparent and customisable through two new shared objects: agent profiles and tasks. Agent responses appear in the familiar comment feature. In a user study (N=30), 14 teams worked on writing projects during one week. Interaction logs and interviews show that teams incorporated agents into existing norms of authorship, control, and coordination, rather than treating them as team members. Agent profiles were viewed as personal territory, while created agents and outputs became shared resources. We discuss implications for team-based AI interaction, highlighting opportunities and boundaries for treating AI as a shared resource in collaborative work.