Problem
Research questions and friction points this paper is trying to address.
AI coding assistants
configurability
developer control
personalization
trust
Configurable AI Coding Assistants: Designing For Developers Who Like to Be in Control
🤖 AI Summary
Current AI programming assistants lack fine-grained control over developer behavioral preferences, limiting their ability to meet professional developers’ demands for controllability and personalization. Addressing this gap, this study synthesizes findings from a survey of 56 developers, seven design workshops, a literature review, and an analysis of existing tools to propose the first systematic four-dimensional configuration framework encompassing code suggestions, system policies, human-AI interaction, and user context. Results indicate that 72.6% of the identified configuration options are perceived as useful by developers, yet only about one-third are currently supported in deployed tools. Notably, task-related controls—such as confidence thresholds and visibility of suggestion quality—are significantly more desired than role-based configurations. These insights inform a task-centered, unified, and discoverable configuration design paradigm to guide the development of next-generation AI programming assistants.
📝 Abstract
AI coding assistants are now widely used in professional development, yet they offer only limited ways for developers to control how they behave. In this paper, we investigate what kinds of configurations experienced developers want in coding assistants, how they prioritize different types of configuration needs, and which interface mechanisms they prefer. We first synthesize product documentation and prior research on trust and personalization to compile a list of 33 configuration options, grouped into four categories: Code suggestions, System & policies, Human-assistant interaction, and Users & their personal context. We then conduct a survey with 56 professional developers and 7 design sessions in which participants arrange configurations into their perfect control board and talk about their needs and experiences in more depth.
Developers report strong interest in configurability: 72.6% of usefulness ratings are positive, while only around a third indicate that the corresponding configuration is known to participants in their tools. Demand is particularly high for task-related controls such as minimum confidence thresholds, visibility of suggestion quality, and response length, whereas many persona-related configurations are seen as unnecessary. In this paper, we discuss the implications for designing more unified and discoverable configuration surfaces for future coding assistants
Innovation
Methods, ideas, or system contributions that make the work stand out.
configurable AI
coding assistants
developer control
personalization
user-centered design
🔎 Similar Papers
No similar papers found.
