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

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.

Related

• More Is Different: Toward a Theory of Emergence in AI-Native Software Ecosystems
• AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering
• FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning
• Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development
• The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE
• SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context

Source: arXiv cs.AI | 2026-04-23