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

TL;DR

This paper introduces Shift-Up, a framework that uses traditional software engineering practices as guardrails to improve AI-native software development, reducing drift and enhancing traceability.

Contribution

It reinterprets established practices like BDD, C4, and ADRs as structural guardrails for GenAI-driven development, supported by initial empirical findings.

Findings

Embedding machine-readable requirements stabilizes agent behavior.

Structured artifacts reduce implementation drift.

Human effort shifts to higher-level design and validation.

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.