Building the Web for Agents: A Declarative Framework for Agent-Web Interaction

TL;DR

This paper introduces VOIX, a declarative web framework that enables websites to securely and reliably expose capabilities to AI agents, improving interaction robustness and privacy.

Contribution

The paper presents VOIX, a novel declarative HTML-based framework that explicitly defines agent capabilities and context, enhancing web-agent interactions.

Findings

Developed <tool> and <context> tags for explicit capability declaration

Participants rapidly built diverse agent-enabled web apps

Framework demonstrated practicality, learnability, and expressiveness

Abstract

The increasing deployment of autonomous AI agents on the web is hampered by a fundamental misalignment: agents must infer affordances from human-oriented user interfaces, leading to brittle, inefficient, and insecure interactions. To address this, we introduce VOIX, a web-native framework that enables websites to expose reliable, auditable, and privacy-preserving capabilities for AI agents through simple, declarative HTML elements. VOIX introduces <tool> and <context> tags, allowing developers to explicitly define available actions and relevant state, thereby creating a clear, machine-readable contract for agent behavior. This approach shifts control to the website developer while preserving user privacy by disconnecting the conversational interactions from the website. We evaluated the framework's practicality, learnability, and expressiveness in a three-day hackathon study with 16 developers. The results demonstrate that participants, regardless of prior experience, were able to rapidly build diverse and functional agent-enabled web applications. Ultimately, this work provides a foundational mechanism for realizing the Agentic Web, enabling a future of seamless and secure human-AI collaboration on the web.