Shift-Up: A Framework for Software Engineering Guardrails in AI-native Software Development -- Initial Findings
This addresses software engineers facing issues with AI-driven development, but it is incremental as it adapts existing practices.
The paper tackles the problem of architectural drift and maintainability in AI-native software development by proposing the Shift-Up framework, which uses software engineering practices as guardrails, and finds that it stabilizes agent behavior and reduces implementation drift.
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.