Enterprises implementing agentic AI face a challenge: Which tools should they permit their agents to make use of, where can they be found, and the way can they be used safely? A brand new protocol, Agentic Resource Discovery, or ARD, goals to let agents answer those questions for themselves. Behind it are Google, Microsoft, Cisco, Nvidia, Salesforce and others.
ARD goals to standardize the best way that tools and services are shared across systems inside a company domain. For instance, when investigating a production problem, an agent will probably want to query engineering documentation and open support tickets, deployment history and observability systems, all of which might be managed by different registries and across different silos. There isn’t any common layer that pulls them together. ARD has been designed to be that layer.
It operates across two levels. Catalogs and Registries. In the primary, a corporation publishes a catalog setting out its available capabilities. The Registries layer act as a type of search engine, crawling those published catalogs.