Building Living Software Systems with Generative & Agentic AI
Jules White
TL;DR
The paper argues that static software is ill-suited to a dynamic world and proposes living software systems powered by generative and agentic AI to continuously translate human goals into actions. It frames translation errors as core bottlenecks across requirements, code, and interfaces, and outlines two pathways: using GenAI to accelerate traditional software development and deploying agentic AI to build truly adaptive systems. A central emphasis is placed on prompts and context, with prompt engineering reframed as learning to express goals and guardrails effectively, plus strategies for fact-checking and human oversight. The work highlights potential for dramatically faster, context-aware software evolution while acknowledging adoption challenges and the need for new interfaces, languages, and training to realize living computing at scale.
Abstract
This paper is an opinion paper that looks at the future of computing in the age of Generative \& Agentic AI. Current software systems are static and inflexible, leading to significant challenges in translating human goals into computational actions. "Living software systems" powered by generative AI offer a solution to this fundamental problem in computing. Traditional software development involves multiple layers of imperfect translation, from business requirements to code, resulting in rigid systems that struggle to adapt to changing user needs and contexts. Generative AI, particularly large language models, can serve as a universal translator between human intent and computer operations. This approach enables the creation of more flexible, context-aware systems that can dynamically evolve to meet user goals. Two pathways for implementing living software systems are explored: using generative AI to accelerate traditional software development, and leveraging agentic AI to create truly adaptive systems. New skills like Prompt Engineering are necessary. By reimagining software as a living, adaptable entity, we can create computing interfaces that are more intuitive, powerful, and responsive to human needs.