Echoes of AI: Investigating the Downstream Effects of AI Assistants on Software Maintainability

TL;DR

This study investigates whether AI assistants like GitHub Copilot impact software maintainability, finding no significant systematic advantages or disadvantages in code evolution, but highlighting areas for future research on potential risks.

Contribution

It provides the first controlled experimental evidence on how AI-assisted development affects subsequent code maintainability in professional settings.

Findings

No significant differences in code evolution time or quality with AI assistance.

AI assistance reduced development time by median 30.7%, with habitual users faster by 55.9%.

No clear evidence of degraded maintainability or warning signs from AI-assisted code.

Abstract

[Context] AI assistants, like GitHub Copilot and Cursor, are transforming software engineering. While several studies highlight productivity improvements, their impact on maintainability requires further investigation. [Objective] This study investigates whether co-development with AI assistants affects software maintainability, specifically how easily other developers can evolve the resulting source code. [Method] We conducted a two-phase controlled experiment involving 151 participants, 95% of whom were professional developers. In Phase 1, participants added a new feature to a Java web application, with or without AI assistance. In Phase 2, a randomized controlled trial, new participants evolved these solutions without AI assistance. [Results] Phase 2 revealed no significant differences in subsequent evolution with respect to completion time or code quality. Bayesian analysis suggests that any speed or quality improvements from AI use were at most small and highly uncertain. Observational results from Phase 1 corroborate prior research: using an AI assistant yielded a 30.7% median reduction in completion time, and habitual AI users showed an estimated 55.9% speedup. [Conclusions] Overall, we did not detect systematic maintainability advantages or disadvantages when other developers evolved code co-developed with AI assistants. Within the scope of our tasks and measures, we observed no consistent warning signs of degraded code-level maintainability. Future work should examine risks such as code bloat from excessive code generation and cognitive debt as developers offload more mental effort to assistants.