Enterprises implementing agentic AI face a persistent challenge: which tools should they allow their agents to use, where can those tools be found, and how can they be used safely? A new protocol, Agentic Resource Discovery (ARD), aims to let agents answer those questions for themselves. Behind it are Google, Microsoft, Cisco, Nvidia, Salesforce, and others.
What ARD Does
ARD aims to standardize the way tools and services are shared across systems within a corporate domain. For example, when investigating a production problem, an agent may want to query engineering documentation, open support tickets, review deployment history, and access observability systems — all of which could be managed by different registries across different silos. There is currently no common layer that pulls them together. ARD has been designed to be that layer.
How It Works
The protocol operates across two levels: Catalogs and Registries. At the first level, an organization publishes a catalog setting out its available capabilities. The Registries layer then acts as a form of search engine, crawling those published catalogs to make resources discoverable by agents.
Getting Started
The ARD specification is available now. Organizations are invited to publish their own catalogs using the quickstart guide, after which they can join the community and participate in the ongoing evolution of the standard.
This article first appeared on InfoWorld.
