# Discovery of Agents With Names (DAWN) - Proposed Charter

Clients often  need to discover information about AI systems and resources (e.g., AI agents) before interacting with them.  This requires obtaining information about how to reach the resources and what they offer.

The focus of the DAWN Working Group (WG) is on how a client can discover public properties of AI resources to facilitate subsequent interactions such as selection, invocation, or communication. DAWN focuses on this initial discovery only and does not include open-ended search, semantic matchmaking, ranking, or selection of an agent based on capabilities or user intent.

Note that discovery may be an iterative process, and may use referrals, direct transfer, delegation, or indirection.

To support these goals, the working group will specify an interoperable and generic discovery mechanism that builds on existing protocols and tools, benefits from established trust models, supports proven delegation and federation architectures, and allows organizations to have independently published discovery information.  The WG will also specify the minimum public discovery information (e.g., type, reachability information, communication protocol, services). 

## Scope 

Discovery in the DAWN WG context is limited to a client requesting discovery details for an AI resource within different use cases (or diameters): 

- within the immediate proximity, e.g., discover all agents in this shop;
- within an organization, e.g., discover all agents for employees for their work at their employer;
- between cooperating parties with trust relationships over the public Internet, e.g., discover all agents of example.org, for all its customers/members. 

The AI resource may be an individual named agent or a service such as a catalog that will further the discovery process.

Where possible, any solutions created by this WG will be built in a modular way using existing IETF protocols that provide support for any needed communication, authentication, and privacy. The WG will consider DNS and mDNS as mechanisms upon which to build a discovery protocol.

The WG work items will provide integrity of all the discovery information exchanged between the DAWN parties.

Although initially focused on discovery of AI agents, the WG should strive to produce results that are general and reusable within other discovery contexts if possible.

## Deliverables

The working group will produce the following standards-track and informational documents. The work on these deliverables is expected to proceed in parallel.

### Terminology (May be published as Informational RFC)

A document describing all the terms used by the other DAWN document. This document may either be published as an informational RFC or be included in the Architecture RFC.

### Use Cases and Applicability (May be published as an Informational RFC)

A document describing broad DAWN use case categories. 

### Discovery Architecture  (Informational RFC(s))
 
One or more documents (possibly one per use case), deployment models, requirements (including the definition of the minimum public discovery information), and the resulting DAWN architecture. 

This deliverable may be held until the Protocol work is considered stable.

### Protocol (Standards Track document(s))

One or more specifications describing the implementations of the Discovery Architecture(s).

## Out of Scope

Specifically out of scope for the DAWN WG during its initial phase are:

- Exchange of capability information beyond the minimum public discovery information, i.e., catalog of capabilities are out of scope.
- All communication beyond the initial discovery process.
- AI resource indexing and searching across the wider Internet.
- Identity management of AI agents, tools, and skills.
- Trust management and trust evaluation methods beyond secure content exchange between DAWN parties.

Future charter for DAWN or other WGs may take on these tasks.

## Coordination with Other Working Groups and Organizations

The DAWN working group will coordinate with WIMSE and OAUTH WG as well as other WGs related to DNS, discovery, identities, or AI. It will also coordinate with external standards bodies as necessary.