Problem
Research questions and friction points this paper is trying to address.
AI-assisted code remediation
socio-technical bottlenecks
continuous integration
code review
large-scale repository
Orchestrating AI-Assisted Code Remediation: Socio-Technical Bottlenecks in a Large Industrial Repository
🤖 AI Summary
This study addresses how AI commoditizes mechanical code editing yet induces continuous integration (CI) overload and code review bottlenecks in large-scale industrial C++ codebases. Through a field study combining a command-line AI coding assistant, Gerrit metadata analysis, developer journals, and qualitative coding, this work systematically investigates the impact of commit granularity on these workflows. The findings reveal that CI capacity, reviewer bandwidth, and change orchestration have emerged as critical bottlenecks, prompting the novel proposition of “semantic changesets” as the fundamental unit of work. Results demonstrate that directory-level batch commits can alleviate CI pressure but necessitate explicit negotiation of review granularity, thereby substantiating the imperative to control change granularity when integrating AI-assisted development into established software engineering pipelines.
📝 Abstract
Background: Code degradation in large, long-lived codebases is costly to remediate through manual refactoring and opportunistic clean-ups. LLM-based coding assistants can perform mechanical remediation at scale, but their impact on industrial workflows is underexplored. Objective: We investigate how massive AI-assisted code remediation affects build-on-commit continuous integration (CI), code review, and team coordination in a large industrial repository, and which socio-technical bottlenecks constrain such remediation when source editing becomes cheap through AI assistance. Method: We report on a 15-day exploratory single-case field study in which an experienced developer used a command-line AI coding buddy to remediate widespread issues in a closed-source industrial C++ repository. We triangulate Gerrit metadata with a developer diary and team chat, analyzed through descriptive statistics and qualitative coding. Results: AI-assisted remediation rapidly generated hundreds of commits touching thousands of lines, saturating CI and reviewer attention. Naïve per-file commits overloaded build-on-commit CI; Switching to directory-based batching and capping the number of files per change restored throughput, but still required explicit review solicitation, negotiation of acceptable commit granularity, and iterative follow-up to resolve build and static-analysis failures. Conclusion: When mechanical editing is cheap, CI capacity, review effort, and change orchestration become primary bottlenecks. Sustainable AI-assisted remediation in very large repositories requires deliberate control of commit, review, and CI batch granularity and treating semantic change sets, such as ``fix all instances of warning X'', as first-class units of work that can be sliced differently for developers, reviewers, and CI.
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI-assisted code remediation
continuous integration
change orchestration
socio-technical bottlenecks
commit granularity
🔎 Similar Papers
No similar papers found.
