Bug Detective and Quality Coach: Developers' Mental Models of AI-Assisted IDE Tools

TL;DR

This study explores developers' mental models of AI-assisted IDE tools for bug detection and readability, revealing their perceptions, trust factors, and design principles to improve human-centered AI integration.

Contribution

It introduces detailed mental models of developers for AI tools in IDEs and proposes design principles to enhance trust and usability.

Findings

Developers see bug detection as 'bug detectives' emphasizing transparency and confidence.

Readability tools are viewed as 'quality coaches' offering personalized guidance.

Trust depends on explanations, timing, and user control.

Abstract

AI-assisted tools support developers in performing cognitively demanding tasks such as bug detection and code readability assessment. Despite the advancements in the technical characteristics of these tools, little is known about how developers mentally model them and how mismatches affect trust, control, and adoption. We conducted six co-design workshops with 58 developers to elicit their mental models about AI-assisted bug detection and readability features. It emerged that developers conceive bug detection tools as \textit{bug detectives}, which warn users only in case of critical issues, guaranteeing transparency, actionable feedback, and confidence cues. Readability assessment tools, on the other hand, are envisioned as \textit{quality coaches}, which provide contextual, personalized, and progressive guidance. Trust, in both tasks, depends on the clarity of explanations, timing, and user control. A set of design principles for Human-Centered AI in IDEs has been distilled, aiming to balance disruption with support, conciseness with depth, and automation with human agency.