From Human Interfaces to Agent Interfaces: Rethinking Software Design in the Age of AI-Native Systems

TL;DR

This paper proposes a paradigm shift in software design from human-centered interfaces to agent-oriented invocation systems, emphasizing formalization, design principles, and architectural implications for AI-native software.

Contribution

It introduces the concept of agent interfaces, formalizes invocable capabilities, and outlines design principles and architectural changes for AI-native software systems.

Findings

Formalization of agent interfaces and invocable capabilities

Design principles including interpretability and composability

Architectural shift towards capability-based, dynamic systems

Abstract

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.