Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Shaolin Wang, Yi Mei, Haoyang Che, He Jiang, Shui Yu, Ying Gu

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.

From Human Interfaces to Agent Interfaces: Rethinking Software Design in the Age of AI-Native 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.
Paper Structure (24 sections, 1 figure, 1 table)

This paper contains 24 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Tool Use and Function Invocation in LLMs
  4. Agentic Programming and Software Engineering Agents
  5. Human--AI Interface and Collaboration Design
  6. Intent-Centric and AI-Assisted Development
  7. Summary
  8. Background and Motivation
  9. Human-Oriented Software Systems
  10. Rise of AI Agents as Software Users
  11. The Core Mismatch
  12. From Human Interfaces to Agent Interfaces
  13. Invocable Capabilities as Fundamental Units
  14. Design Principles for AI-Oriented Software
  15. Machine Interpretability
  16. ...and 9 more sections

Figures (1)

  • Figure 1: Evolution of software interaction paradigms. The proposed shift is not merely from GUI to API, but from feature-centric applications consumed by humans to capability-oriented systems invoked and dynamically composed by AI agents.