Shift-Up: A Framework for Software Engineering Guardrails in AI-native Software Development -- Initial Findings
Petrus Lipsanen, Liisa Rannikko, François Christophe, Konsta Kalliokoski, Vlad Stirbu + 1 more
TLDR
Shift-Up is a framework that uses traditional software engineering practices as guardrails to stabilize AI-native development, reducing drift and improving maintainability.
Key contributions
- Proposes Shift-Up, a framework reinterpreting SE practices (BDD, C4, ADRs) as guardrails for GenAI development.
- Addresses architectural drift, traceability, and maintainability issues in AI-native software engineering.
- Evaluation shows Shift-Up stabilizes agent behavior and reduces implementation drift compared to vibe coding.
- Shifts human effort towards higher-level design and validation in AI-assisted development.
Why it matters
This paper is crucial for mitigating challenges in AI-native software development, like architectural drift and maintainability. It shows established SE practices can effectively control generative AI agents, leading to more stable and traceable systems. This shifts human focus to higher-level design, improving efficiency and quality.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.