Software as Content: Dynamic Applications as the Human-Agent Interaction Layer

TL;DR

This paper proposes Software as Content (SaC), a new paradigm where dynamic, persistent applications serve as the primary interface for human-agent interaction, overcoming limitations of traditional chat-based systems.

Contribution

It introduces the SaC paradigm, formalizes the interaction model, and demonstrates a system architecture that enables dynamic, task-specific software interfaces for improved human-AI collaboration.

Findings

SaC enables persistent, evolving interaction interfaces.

Demonstrates technical viability across various tasks.

Identifies conditions where natural language is preferable.

Abstract

Chat-based natural language interfaces have emerged as the dominant paradigm for human-agent interaction, yet they fundamentally constrain engagement with structured information and complex tasks. We identify three inherent limitations: the mismatch between structured data and linear text, the high entropy of unconstrained natural language input, and the lack of persistent, evolving interaction state. We introduce Software as Content (SaC), a paradigm in which dynamically generated agentic applications serve as the primary medium of human-agent interaction. Rather than communicating through sequential text exchange, this medium renders task-specific interfaces that present structured information and expose actionable affordances through which users iteratively guide agent behavior without relying solely on language. These interfaces persist and evolve across interaction cycles, transforming from transient responses into a shared, stateful interaction layer that progressively converges toward personalized, task-specific software. We formalize SaC through a human-agent-environment interaction model, derive design principles for generating and evolving agentic applications, and present a system architecture that operationalizes the paradigm. We evaluate across representative tasks of selection, exploration, and execution, demonstrating technical viability and expressive range, while identifying boundary conditions under which natural language remains preferable. By reframing interfaces as dynamically generated software artifacts, SaC opens a new design space for human-AI interaction, positioning dynamic software as a concrete and tractable research object.