Discovery of Agents, Workloads, and Named entities
bofreq-farrel-discovery-of-agents-workloads-and-named-entities-00

The information below is for an older version of this BOF request.
Document Type Proposed BOF request Snapshot
Title Discovery of Agents, Workloads, and Named entities
Last updated 2026-05-07
State Proposed
Editors
Responsible leadership
Send notices to (None)
bofreq-farrel-discovery-of-agents-workloads-and-named-entities-00

Name: Discovery of Agents, Workloads, and Named entities (DAWN)

Description

Many distributed processing environments depend on the interaction
between components that do not have pre-configured capability,
location, or reachability relationships. In order for these systems
to operate correctly, the components must be able to discover each
other. For complete generality, we call these components "entities".
Entities may be tasks, workloads, endpoints, services, AI agents, etc.

In each case, an entity needs knowledge of remote entities before
interaction can proceed: what they are, what they offer, and whether
they can be trusted. Such knowledge could be obtained through static
configuration, but this approach is impractical at scale and across
organisational boundaries. Existing discovery mechanisms, particularly
those used for service or endpoint discovery, provide only limited
information such as basic identity and reachability. More advanced
entity discovery use cases may require discovery of richer descriptive
properties such as the tasks an entity is able to handle, supported
interaction modes and protocols, lifecycle properties, and whether
the entity may invoke other tools, services, or agents, rather than
only executing fixed pre-programmed functions.

An automated and interoperable discovery mechanism is needed that builds
on existing protocols and tools, benefits from an established trust model,
supports proven delegation and federation architectures, and allows
organisations to independently publish discovery information.

Providing a decentralised and interoperable discovery mechanism is
essential to protecting the openness of the Internet and protecting
against dominance by a single or a small number of providers. It will
also facilitate interoperability between systems of entities from
different sources. Integral to this is building a governance system
for the registration of entities.

This BoF seeks to build consensus around establishing a working group
to develop requirements, information models, and protocol solutions for
entity discovery.

Required Details

Information for IAB/IESG

To allow evaluation of your proposal, please include the following items:

  • Any protocols or practices that already exist in this space
  • Semi-private AI agent-to-agent ecosystems include forms of discovery
    such as may be seen in

  • DNS already performs a similar discovery mechanism and several
    proposals exist to make it applicable, such as

  • Which (if any) modifications to existing protocols or practices are required.

  • It would be up to the working group to determine what requirements need
    to be addressed, which protocol(s) form the best starting point, and
    what extensions are needed.

    • Regardless of the solution chosen, a common Information Madel will be
      needed to structure the discovered information.

  • Which (if any) entirely new protocols or practices are required

  • See previous answers.

  • Open source projects (if any) implementing this work

  • See previous answers.

Agenda

Very early draft:

  1. Administrivia and purpose of the BoF
  2. Scene-setting and terminology
  3. Problem statement
  4. Overview of categories of use cases
  5. Solution requirements
  6. Potential solution space
  7. Draft charter
  8. Open discussion