Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Software
This addresses the problem of designing effective in-application assistants for users of feature-rich software, offering incremental insights into balancing automation with user control.
The study investigated two automation paradigms for LLM-based copilots in software, finding that a semi-automated copilot outperformed a fully automated one in user control, utility, and learnability for exploratory tasks, while the fully automated version saved time for simpler tasks.
Large Language Model (LLM)-based in-application assistants, or copilots, can automate software tasks, but users often prefer learning by doing, raising questions about the optimal level of automation for an effective user experience. We investigated two automation paradigms by designing and implementing a fully automated copilot (AutoCopilot) and a semi-automated copilot (GuidedCopilot) that automates trivial steps while offering step-by-step visual guidance. In a user study (N=20) across data analysis and visual design tasks, GuidedCopilot outperformed AutoCopilot in user control, software utility, and learnability, especially for exploratory and creative tasks, while AutoCopilot saved time for simpler visual tasks. A follow-up design exploration (N=10) enhanced GuidedCopilot with task-and state-aware features, including in-context preview clips and adaptive instructions. Our findings highlight the critical role of user control and tailored guidance in designing the next generation of copilots that enhance productivity, support diverse skill levels, and foster deeper software engagement.