From Human Interfaces to Agent Interfaces: Rethinking Software Design in the Age of AI-Native Systems
This addresses a foundational problem for software engineers and AI developers by rethinking design principles in the age of AI, though it is conceptual and incremental in building on existing trends.
The paper tackles the shift in software design from human-oriented interfaces to agent-oriented systems due to the rise of AI agents, proposing formal concepts like agent interfaces and invocable capabilities to establish a foundation for AI-native software.
Software systems have traditionally been designed for human interaction, emphasizing graphical user interfaces, usability, and cognitive alignment with end users. However, recent advances in large language model (LLM)-based agents are changing the primary consumers of software systems. Increasingly, software is no longer only used by humans, but also invoked autonomously by AI agents through structured interfaces. In this paper, we argue that software engineering is undergoing a paradigm shift from human-oriented interfaces to agent-oriented invocation systems. We formalize the notion of agent interfaces, introduce invocable capabilities as the fundamental building blocks of AI-oriented software, and outline design principles for such systems, including machine interpretability, composability, and invocation reliability. We then discuss architectural and organizational implications of this shift, highlighting a transition from monolithic applications to capability-based systems that can be dynamically composed by AI agents. The paper aims to provide a conceptual foundation for the emerging paradigm of AI-native software design.