Towards Shift-Up: A Framework and a Prestudy on High-Value Activities in GenAI Native Software Development

2025-09-29

AI Summary

Generative AI (GenAI) risks trapping developers in low-value coding tasks rather than empowering them to engage in high-value cognitive activities. Method: This paper proposes the “shift-up” framework, advocating a strategic elevation of development focus from low-level implementation toward higher-order activities—including system design, architectural decision-making, and quality assurance. It introduces the first systematic definition of a GenAI-native development paradigm, realized through a prompt engineering framework built upon existing large language models and an environment enabling collaboration between domain-specialized AI agents. Contribution/Results: Preliminary experiments demonstrate that the framework significantly increases team investment in high-value activities—such as requirements analysis, interface design, and technology selection—while maintaining code quality. This work establishes both a theoretical foundation and a practical pathway for human-centered, AI-augmented software development methodologies.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Generative AI (GenAI) has significantly influenced software engineering. Associated tools have created a shift in software engineering, where specialized agents, based on user-provided prompts, are replacing human developers. In this paper, we propose a framework for GenAI native development that we call extit{shift-up}, which helps software teams focus on high-value work while being supported by GenAI. Furthermore, we also present a preliminary study testing these ideas with current GenAI tools. Towards the end of the paper, we propose future research goals to study shift-up in more detail.

Problem

• Proposes shift-up framework for GenAI native development
• Helps software teams focus on high-value activities
• Studies how GenAI can support developers effectively

Innovation

• Framework enables shift-up for GenAI native development
• Focuses teams on high-value work with GenAI support
• Preliminary study validates framework with current tools