Google and Industry Partners Announce Agentic Resource Discovery Specification for AI Agents
Google and industry partners have introduced the Agentic Resource Discovery (ARD) specification to help AI agents discover and verify tools and APIs. The framework uses catalogs and registries to improve governance and security in autonomous agent workflows.
Why it matters
Standardizing how AI agents find and interact with tools is a critical step toward building secure, interoperable, and scalable enterprise AI ecosystems.
InfoQ Homepage News Google and Industry Partners Announce Agentic Resource Discovery Specification for AI Agents
While protocols such as the Model Context Protocol (MCP) define how an AI agent invokes a tool, ARD addresses an earlier stage in the lifecycle: how agents discover those tools in the first place. Rather than replacing existing standards, ARD is designed as a complementary discovery layer that works across frameworks and providers.
Srinivas Krishnan , Distinguished Engineer at Google Cloud, highlights the motivation for ARD:
The problem is simple to state and hard to solve, especially in the enterprise, where the answer can't just be 'find something that works.' It has to be governed, with security and identity built in rather than bolted on.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in