Shift-Up: A Framework for Software Engineering Guardrails in AI-native Software Development -- Initial Findings
Petrus Lipsanen, Liisa Rannikko, Fran\c{c}ois Christophe, Konsta Kalliokoski, Vlad Stirbu, Tommi Mikkonen
Why It Matters
What makes this one worth your time
As generative AI transforms software engineering, establishing effective frameworks like Shift-Up is crucial for maintaining code quality and project sustainability.
Shift-Up offers a structured approach to stabilize AI-driven software development.
Summary
The paper introduces Shift-Up, a framework that applies established software engineering practices as guardrails for AI-native software development, aiming to mitigate issues like architectural drift and maintainability in generative AI implementations.
Key contributions
- Proposes the Shift-Up framework for AI-native software development.
- Compares unstructured vibe coding with structured prompt engineering and the Shift-Up approach.
- Demonstrates the effectiveness of traditional software engineering artifacts in AI-assisted development.
Notable insights
- The integration of machine-readable requirements can enhance agent behavior and reduce implementation drift.
- Reinterpreting traditional software engineering practices as guardrails is a novel approach to address challenges in AI-native development.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2604.20436v1 Announce Type: cross 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.