{"slug": "solving-an-ard-problem-in-ai-agentic-resource-discovery", "title": "Solving an ARD problem in AI: Agentic Resource Discovery", "summary": "Google, Microsoft, Cisco, Nvidia, and Salesforce have launched Agentic Resource Discovery (ARD), a new protocol that enables AI agents to autonomously discover and use tools and services across enterprise systems. ARD standardizes resource sharing through Catalogs and Registries layers, solving the challenge of integrating disparate tools for agentic AI workflows.", "body_md": "Enterprises [implementing agentic AI](https://www.infoworld.com/article/4162871/the-agentic-ai-frenzy-increases-as-more-vendors-stake-their-claims.html) face a challenge: [Which tools](https://www.computerworld.com/article/3617392/what-are-ai-agents-and-why-are-they-now-so-pervasive.html) should they allow their agents to use, where can they be found, and how can they be used safely? A new protocol, [Agentic Resource Discovery](https://agenticresourcediscovery.org/), or ARD, aims to let agents answer those questions for themselves. Behind it are Google, Microsoft, Cisco, Nvidia, Salesforce and others.\n\nARD aims to standardize the way that 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 and open support tickets, deployment history and observability systems, all of which could be managed by different registries and across different silos. There is no common layer that pulls them together. ARD has been designed to be that layer.\n\nIt operates across two levels. Catalogs and Registries. In the first, an organization publishes a catalog setting out its available capabilities. The Registries layer act as a form of search engine, crawling those published catalogs.\n\nThe ARD specification is available now. Organizations are invited to publish their own catalogs using [the quickstart guide](https://agenticresourcediscovery.org/how_to_publish/#step-1-create-the-manifest-ai-catalogjson). After this, they are able [to join the community](https://github.com/ards-project/ard-spec) and participate in the evolution of ARD.", "url": "https://wpnews.pro/news/solving-an-ard-problem-in-ai-agentic-resource-discovery", "canonical_source": "https://www.infoworld.com/article/4187305/solving-an-ard-problem-in-ai-agentic-resource-discovery.html", "published_at": "2026-06-19 16:37:02+00:00", "updated_at": "2026-06-19 16:38:55.365543+00:00", "lang": "en", "topics": ["ai-agents", "ai-infrastructure", "ai-tools", "ai-research"], "entities": ["Google", "Microsoft", "Cisco", "Nvidia", "Salesforce", "Agentic Resource Discovery", "ARD"], "alternates": {"html": "https://wpnews.pro/news/solving-an-ard-problem-in-ai-agentic-resource-discovery", "markdown": "https://wpnews.pro/news/solving-an-ard-problem-in-ai-agentic-resource-discovery.md", "text": "https://wpnews.pro/news/solving-an-ard-problem-in-ai-agentic-resource-discovery.txt", "jsonld": "https://wpnews.pro/news/solving-an-ard-problem-in-ai-agentic-resource-discovery.jsonld"}}