Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Software

Abstract

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.

Accepted for publication in the CHI Conference on Human Factors in Computing Systems (CHI 2025), April 26 - May 1, 2025, Yokohama, Japan

References in corpus (6)

• Calendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loop
• Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking
• How Readable is Model-generated Code? Examining Readability and Visual Inspection of GitHub Copilot
• Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition
• Ivie: Lightweight Anchored Explanations of Just-Generated Code
• Challenges in Human-Agent Communication