ATeam: Governance-Aware LLM-Assisted Software Sustaining Engineering for Enterprise Systems

Abstract

AI-assisted software development approaches, such as vibe coding, enable rapid code generation but lack the governance and reliability required for sustaining engineering in enterprise software. In these environments, traceability, security, technical debt management, and architectural integrity are critical for any software modification. This paper presents ATeam, a framework that facilitates AI-assisted software development through a structured and auditable maintenance process incorporating human oversight. The framework employs a multi-phase pipeline that enforces impact analysis and explicit approval gates. ATeam is evaluated on 24 sustaining engineering tasks spanning four IEEE maintenance categories, utilizing three distinct large language models (LLMs). A set of interdependent microservices is developed to assess the system. ATeam achieves an 82.5 end-to-end score. The results demonstrate that structured decomposition and governance reduce dependence on model scale, with smaller models remaining competitive with larger ones. This finding enables regulated industries to leverage AI-assisted development using on-premises models. Comparative evaluation against AutoGPT-style and unconstrained baselines reveals that ATeam achieves statistically significant improvements (Welch's $p<10^{-6})$ with large effect sizes. The evidence suggests that governance, rather than agentic execution alone, is the primary determinant of reliable enterprise software sustaining engineering.