English

Shift-Up: A Framework for Software Engineering Guardrails in AI-native Software Development -- Initial Findings

Software Engineering 2026-04-23 v1 Artificial Intelligence

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.

Keywords

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

R2 v1 2026-07-01T12:30:12.386Z