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

2026-04-22

AI Summary

This work addresses the pervasive challenges of architectural drift, poor traceability, and declining maintainability in AI-native software development by introducing the Shift-Up framework. Shift-Up systematically translates established software engineering practices—namely Behavior-Driven Development (BDD), the C4 architectural model, and Architecture Decision Records (ADRs)—into machine-readable, structured guardrails embedded within generative AI agent workflows. Leveraging structured prompt engineering and the Design Science Research (DSR) methodology, the framework effectively constrains and guides AI agent behavior, substantially mitigating implementation drift while enhancing system stability and maintainability. This enables developers to focus on high-level architectural design and validation, thereby improving overall software quality.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Generative AI
• architectural drift
• traceability
• maintainability
• AI-native software development

Innovation

• AI-native development
• software engineering guardrails
• executable requirements
• architectural modeling
• design science research