Meeting · IETF 127
DAWN WG at IETF 127
San Francisco, US · November 14 to 20, 2026
15 drafts on the agenda, 15 reviewed here. Reviewed drafts have a short summary and a link to the full review. The rest show the draft's own abstract. Official agenda, revision 08 →
Agenda as of November 16, 2026. It can change before the meeting.
Thursday, November 19, 4:30pm to 6:30pm Pacific 13 slots
Remarks from the chairs
Terminology for the Discovery of Agents With Names
draft-farrel-dawn-terminology -07
DAWN Terminology (draft-farrel-dawn-terminology-04)
As distributed systems proliferate — including AI agents, cloud workloads, software services, and network functions — there is no consistent shared vocabulary for talking about how entities discover each other. This draft defines a common terminology for the DAWN (Discovery of Agents, Workloads, and Named Entities) working group, so that related DAWN documents can use terms consistently without each document needing to re-litigate definitions.
Use Cases and Applicability for Discovery of Agents With Names
This draft catalogs use cases for the Discovery of Agents, Workloads, and Named Entities (DAWN) — the general problem of how one entity (an AI agent, workload, service, or human operator) locates another entity that can satisfy a specific need. The core insight is that in increasingly distributed and agentic computing environments, static configuration is insufficient; entities need a runtime mechanism to discover peers, tools, and resources by capability, policy, jurisdiction, or resource type.
Discovery of AI Agents for Communication Services: Use Case and Problem Statement
draft-jadoon-dawn-layered-agent-discovery -00
DAWN Use Case for Protocol-Layer AI Agents
An organization runs several AI agents that each help with one part of the network stack. One tunes application media. One helps with transport adaptation. One helps with routing. One helps with packet scheduling.
Two of them might both advertise "traffic optimization". A discovering agent cannot tell which one works on transport and which one works on routing.
A Framework for Agent Discovery in DAWN
draft-zhang-dawn-agent-discovery-framework -09
A Two-Layer Agent Discovery Framework for DAWN
DAWN has many discovery proposals and no agreed picture of how they fit together. This draft offers that picture: local discovery inside a domain, DNS between domains, and a gateway in each domain that decides what leaves.
Minimum Public Discovery Information: Requirements and Common Semantics
MDI Information Model for DAWN
The DAWN working group has defined a concept called Minimum Discoverable Information (MDI) — the minimal set of metadata a discovering party needs to identify, triage, and reach an entity (agent, service, or workload) — but no DAWN document has actually specified what fields MDI contains. In practice, this gap is being filled incompatibly: DNS-based bootstrap, well-known JSON manifests, agent cards, and signed capability documents each carry slightly different minimal field sets with no common structure. This draft proposes a single, encoding-neutral abstract information model to serve as the common denominator.
DNS for AI Discovery / Zero-Configuration Agent Discovery / Common Agent DNS Discovery Parameters
draft-mozleywilliams-dawn-dnsaid -00
DNS for AI Discovery (DNS-AID) with SVCB Records
An agent wants to call another agent. It needs the endpoint, the agent protocol (MCP, A2A), and a pointer to the agent's descriptor. Today that comes from configuration or a third-party directory.
DNS-AID publishes it in DNS, in records the agent's own organization controls. It uses SVCB records and defines no new record types.
draft-jakab-dawn-agent-discovery-mdns -01
Zero-Configuration Agent Discovery via mDNS
Current agent-to-agent communication protocols (A2A, MCP) assume the connecting party already knows the agent's hostname or URL. This spec addresses the gap for local-network environments — developer workstations, branch offices, meeting rooms, edge deployments — where agents start, stop, and move dynamically and where there is no central registry or manual configuration available. The proposed solution is zero-configuration discovery using existing mDNS (RFC 6762) and DNS-SD (RFC 6763) mechanisms.
draft-blwm-dawn-common-discovery-parameters -00
Common DNS Discovery Parameters for Agents
DAWN has two DNS-based discovery proposals. DNS-AID publishes agents in unicast DNS with SVCB records. Zero-Configuration Agent Discovery advertises them on the local link with mDNS and DNS-SD TXT records. Each had its own key names.
This draft defines one set of nine keys for both.
DNS-Based Agent Naming (DAN): AIDISCA and AIINDEX Resource Records for AI Agent Discovery
DNS-Based Agent Naming (DAN): AIDISCA and AIINDEX Resource Records
AI agents operating across different organizations and internet domains have no standardized mechanism to discover one another's network endpoints and capabilities. This draft addresses the bootstrapping phase only — getting an agent's address and a coarse capability description before any connection is made — leaving richer runtime semantics to the protocols themselves (MCP, A2A). It proposes using DNS as the publication layer via two new resource record types.
BEST: The Behavioral State Protocol
draft-dinuzzo-best-protocol -03
BEST, an Agent Interaction Protocol in a Discovery Slot
An AI agent that has never seen a service needs to be told, out of band, which operations it accepts, what the payloads look like, and how to get a credential.
BEST wants an agent to get from a domain name to working use by itself. The person says "use example.com". The agent fetches a manifest, reads the catalogue of operations, signs the person in, and starts sending commands (Section 1).
Registry-Assisted Resolution for Known Subjects Without DNS Discovery Anchors
draft-raskar-agentic-web-federated-resolution -02
Registry-Assisted Resolution for Agents Without a DNS Anchor
Most DAWN proposals assume the publisher controls a DNS zone. Alice at
[email protected]does not. Neither does a workload with a SPIFFE ID or a DID.This draft covers that case. The client already knows the subject's identifier and asks a configured registry where the subject's agent descriptor lives.
Agent Resource Discovery (ARD): Architecture, Initial Contact, and Lookup
draft-bu-dawn-ard-architecture -00
Agent Resource Discovery (ARD) Architecture
An agent cannot load every MCP server, A2A agent and skill into its context window. The tool list has to be found at runtime, across organizations, without one company running the directory.
ARD's answer is a search layer. Publishers describe their resources in a JSON manifest. Registries index those manifests. A consumer sends a query and gets back the top few entries.
draft-jimenez-dawn-ard-initial-contact -00
ARD Initial Contact: Finding the Agent Manifest
ARD puts an organization's agents, MCP servers and skills in one JSON manifest. A client needs the URL of that manifest before it can do anything else.
This draft defines how the client gets that URL from a domain name, from the local network, or from configuration. It stops there. "Initial contact ends at the manifest" (Section 3).
draft-bu-dawn-ard-discovery -00
ARD Manifest and Lookup for Agent Discovery
An agent needs to find MCP servers, A2A agents and skills it was not configured with. This draft defines the catalog format a publisher serves and the HTTP search API a registry exposes.
Considerations for Agent Gateway Integration within the DAWN Framework
draft-miao-dawn-agw-intergration-consideration -00
Agent Gateways as Discovery Proxies in DAWN
Agents behind a NAT or firewall cannot publish themselves in public DNS. Small agents may not be able to run wide-area discovery at all.
This draft puts an Agent Gateway (AGW) at the domain boundary to do discovery for them. Outbound, it looks up remote agents on behalf of local ones. Inbound, it answers for the agents behind it and hides their addresses.
Conclusion, next steps, review of all candidate proposals against the DAWN deliverables