Shift-Up: A Framework for Software Engineering Guardrails in AI-native Software Development -- Initial Findings
Abstract
Generative AI (GenAI) is reshaping software engineering by shifting development from manual coding toward agent-driven implementation. While vibe coding promises rapid prototyping, it often suffers from architectural drift, limited traceability, and reduced maintainability. Applying the design science research (DSR) methodology, this paper proposes Shift-Up, a framework that reinterprets established software engineering practices, like executable requirements (BDD), architectural modeling (C4), and architecture decision records (ADRs), as structural guardrails for GenAI-native development. Preliminary findings from our exploratory evaluation compare unstructured vibe coding, structured prompt engineering, and the Shift-Up approach in the development of a web application. These findings indicate that embedding machine-readable requirements and architectural artifacts stabilizes agent behavior, reduces implementation drift, and shifts human effort toward higher-level design and validation activities. The results suggest that traditional software engineering artifacts can serve as effective control mechanisms in AI-assisted development.
Cite
@article{arxiv.2604.20436,
title = {Shift-Up: A Framework for Software Engineering Guardrails in AI-native Software Development -- Initial Findings},
author = {Petrus Lipsanen and Liisa Rannikko and François Christophe and Konsta Kalliokoski and Vlad Stirbu and Tommi Mikkonen},
journal= {arXiv preprint arXiv:2604.20436},
year = {2026}
}
Comments
This paper has been accepted for presentation at the VibeX 2026 International Workshop on Vibe Coding and Vibe Researching