From Teacher to Colleague: How Coding Experience Shapes Developer Perceptions of AI Tools
Ilya Zakharov, Ekaterina Koshchenko, Agnia Sergeyuk
TL;DR
This study investigates how coding experience relates to AI tool adoption and to the roles developers ascribe to AI in their workflows using data from the JetBrains State of Developer Ecosystem Report 2024 (n≈3380 for role analysis). It finds that coding experience barely predicts awareness or adoption of AI tools, but strongly modulates the perceived roles of AI: experienced developers are more likely to view AI as a junior colleague, content generator, or to assign no role, while novices tend to see AI as a teacher. The analysis combines Spearman correlations and logistic regression with FDR control to reveal nuanced links between expertise and mental models. The findings highlight the need to tailor AI tooling to users’ expertise levels to foster meaningful adoption and effective collaboration between humans and AI.
Abstract
AI-assisted development tools promise productivity gains and improved code quality, yet their adoption among developers remains inconsistent. Prior research suggests that professional expertise influences technology adoption, but its role in shaping developers' perceptions of AI tools is unclear. We analyze survey data from 3380 developers to examine how coding experience relates to AI awareness, adoption, and the roles developers assign to AI in their workflow. Our findings reveal that coding experience does not predict AI adoption but significantly influences mental models of AI's role. Experienced developers are more likely to perceive AI as a junior colleague, a content generator, or assign it no role, whereas less experienced developers primarily view AI as a teacher. These insights suggest that AI tools must align with developers' expertise levels to drive meaningful adoption.