<?xml version="1.0" encoding="UTF-8"?>
  <?xml-stylesheet type="text/xsl" href="rfc2629.xslt" ?>
  <!-- generated by https://github.com/cabo/kramdown-rfc version 1.7.43 (Ruby 3.3.12) -->


<!DOCTYPE rfc  [
  <!ENTITY nbsp    "&#160;">
  <!ENTITY zwsp   "&#8203;">
  <!ENTITY nbhy   "&#8209;">
  <!ENTITY wj     "&#8288;">

]>


<rfc ipr="trust200902" docName="draft-kay-dawn-use-cases-02" category="info" submissionType="IETF" tocInclude="true" sortRefs="true" symRefs="true">
  <front>
    <title abbrev="DAWN Use Cases">Use Cases and Applicability for Discovery of Agents With Names</title>

    <author initials="D." surname="King" fullname="Daniel King">
      <organization>Lancaster University</organization>
      <address>
        <email>d.king@lancaster.ac.uk</email>
      </address>
    </author>
    <author initials="K." surname="Yao" fullname="Kehan Yao">
      <organization>China Mobile</organization>
      <address>
        <email>yaokehan@chinamobile.com</email>
      </address>
    </author>
    <author initials="K." surname="Adler" fullname="Ken Adler">
      <organization>Indeed</organization>
      <address>
        <email>kadler@indeed.com</email>
      </address>
    </author>
    <author initials="R." surname="Ramdhany" fullname="Rajiv Ramdhany">
      <organization>BBC</organization>
      <address>
        <email>rajiv.ramdhany@bbc.co.uk</email>
      </address>
    </author>
    <author initials="L." surname="Jakab" fullname="Loránd Jakab">
      <organization>Cisco Systems</organization>
      <address>
        <email>lojakab@cisco.com</email>
      </address>
    </author>
    <author initials="L." surname="Dunbar" fullname="Linda Dunbar">
      <organization>Futurewei</organization>
      <address>
        <email>ldunbar@futurewei.com</email>
      </address>
    </author>

    <date year="2026" month="November" day="16"/>

    <area>Internet</area>
    <workgroup>Discovery of Agents With Names</workgroup>
    <keyword>discovery</keyword> <keyword>agents</keyword> <keyword>workloads</keyword> <keyword>named entities</keyword> <keyword>DAWN</keyword>

    <abstract>


<?line 58?>

<t>This document describes use cases and applicability for Discovery of Agents
With Names (DAWN). It illustrates how clients discover AI resources and obtain
the minimum information needed for subsequent interaction within a local
network, within an organisation, or between cooperating organisations with
trust relationships.</t>

<t>This document does not define a discovery protocol, a registration procedure, a
selection algorithm, or an agent-to-agent communication protocol.</t>



    </abstract>

    <note title="About This Document" removeInRFC="true">
      <t>
        Status information for this document may be found at <eref target="https://datatracker.ietf.org/doc/draft-kay-dawn-use-cases/"/>.
      </t>
      <t>
        Discussion of this document takes place on the
        Discovery of Agents With Names Working Group mailing list (<eref target="mailto:dawn@ietf.org"/>),
        which is archived at <eref target="https://mailarchive.ietf.org/arch/browse/dawn/"/>.
        Subscribe at <eref target="https://www.ietf.org/mailman/listinfo/dawn/"/>.
      </t>
    </note>


  </front>

  <middle>


<?line 69?>

<section anchor="introduction"><name>Introduction</name>

<t>Artificial Intelligence (AI) systems may depend on resources whose capabilities,
locations, or communication methods are not configured in advance. Discovery
allows a client to locate a resource and obtain the minimum information needed
to attempt a subsequent interaction.</t>

<t>Discovery of Agents With Names (DAWN) initially focuses on AI agents and their
capabilities, including discovery of other resources used in AI systems. This
document uses "entity" for a discoverable component in that context. Such
entities may include agents, tools, services, tasks, data sources, models,
inference services, workloads, brokers, and application endpoints. Skills may be
discoverable attributes of those entities. Reuse in other discovery contexts is
desirable, but does not extend the initial scope to general resource discovery.</t>

<t>The DAWN problem statement <xref target="I-D.akhavain-moussa-dawn-problem-statement"/>
provides background for this work. These use cases are intended as a common
foundation for the DAWN requirements <xref target="I-D.king-dawn-requirements"/> and for
the Discovery Architecture, which will define the minimum discovery
information. The mapping between requirements and use cases is maintained in
the requirements document, not here.</t>

<t>This document first presents four scenarios in <xref target="scenarios"/>. It then draws out
the discovery characteristics and common pattern they share, and defines the
following categories of entity discovery:</t>

<t><list style="numbers" type="1">
  <t>Capability-Oriented Discovery, where an entity needs to discover another
entity that can provide a function or capability.</t>
  <t>Resource-Oriented Discovery, where discovery identifies resources
used in AI systems.</t>
  <t>Administrative Scope Extensions, where discovery crosses organisational,
delegation, or tenancy boundaries within the applicable trust relationships.</t>
  <t>Operational Discovery, where discovery supports operation, audit,
troubleshooting, compliance, or automation.</t>
</list></t>

<t>The first two categories are base cases. The others describe common extensions
or deployments of those base cases.</t>

<t>Other Internet-Drafts describe agentic AI discovery use cases and communication
protocol requirements, including <xref target="I-D.mozley-aidiscovery"/>,
<xref target="I-D.agentic-ai-usecases-requirements"/>, and
<xref target="I-D.scrm-aiproto-usecases"/>.</t>

</section>
<section anchor="limitations-of-this-document"><name>Limitations of this Document</name>

<t>This document describes discovery within a local network, within an
organisation, or between cooperating organisations with trust relationships
over the public Internet. It does not describe the full lifecycle of an entity
or establish those trust relationships.</t>

<t>The following are in scope:</t>

<t><list style="symbols">
  <t>discovery of a specific named AI resource;</t>
  <t>discovery of candidate AI resources by capability or other discovery
properties within the applicable deployment;</t>
  <t>discovery of tasks as resources in an AI system;</t>
  <t>discovery initiated by an agent, workload, service, application, or human
operator;</t>
  <t>discovery of supporting resources used by AI agents and applications;</t>
  <t>exchange of the minimum discovery information, directly or by indirection,
before selection, invocation, or communication can take place.</t>
</list></t>

<t>The following are out of scope:</t>

<t><list style="symbols">
  <t>registration of entities for discovery;</t>
  <t>authentication or attestation of registrations;</t>
  <t>design, definition, or governance of naming systems;</t>
  <t>identity management of AI agents, tools, and skills;</t>
  <t>trust management and trust evaluation beyond protecting content exchanged
between discovery participants;</t>
  <t>selection among candidate entities returned by discovery;</t>
  <t>exchange of capability information beyond the minimum discovery information
defined by the Architecture work;</t>
  <t>capability negotiation after discovery;</t>
  <t>all application communication beyond the discovery process;</t>
  <t>task orchestration;</t>
  <t>standalone certificate or key lookup services; and</t>
  <t>AI resource indexing across the wider Internet, general search, ranking,
or marketplace discovery.</t>
</list></t>

<t>Clients may query an organisation's catalogue or a cooperating discovery
service within these boundaries. They may follow references to obtain minimum
discovery information. Fetching a richer capability description is a subsequent
application exchange, even when discovery supplies its reference.</t>

</section>
<section anchor="terminology"><name>Terminology</name>

<t>Terminology for DAWN is defined in <xref target="I-D.farrel-dawn-terminology"/>.</t>

<t>Attention is drawn to the following specific terms defined in
<xref target="I-D.farrel-dawn-terminology"/> that are key to this document:</t>

<t><list style="symbols">
  <t>discovering entity</t>
  <t>discovered entity</t>
  <t>discoverable object</t>
  <t>discovery information</t>
  <t>minimum discoverable information</t>
</list></t>

<t>The client initiating discovery is the discovering entity. In this document,
"minimum discovery information" refers to the minimum discoverable information
whose content is to be defined by the Architecture requirements.</t>

<t>The scenarios in <xref target="scenarios"/> also use the following implementation term:</t>

<dl>
  <dt>Agent harness</dt>
  <dd>
    <t>Software that supports an AI agent's execution, such as interaction with
models, invocation of tools, management of context and state, and application
of execution controls. It may support discovery on behalf of the agent. This
document does not specify its internal operation. Open-source examples of an
agent harness include OpenClaw and Hermes.</t>
  </dd>
</dl>

</section>
<section anchor="applicability"><name>Applicability</name>

<t>The categories in <xref target="categories-of-discovery"/> apply in three settings:</t>

<texttable>
      <ttcol align='left'>Deployment</ttcol>
      <ttcol align='left'>Illustrative discovery need</ttcol>
      <ttcol align='left'>Applicability condition</ttcol>
      <c>Local network</c>
      <c>An assistant finds a nearby inference service advertised on its local network.</c>
      <c>Discovery visibility is local; using the service remains subject to application permissions.</c>
      <c>Within an organisation</c>
      <c>An enterprise assistant finds an internal data source or tool.</c>
      <c>Publication and access follow the organisation's existing administrative and trust arrangements.</c>
      <c>Between cooperating organisations</c>
      <c>An assistant finds a partner's calendar-coordination agent.</c>
      <c>The organisations have a trust relationship; discovery finds resources within that relationship.</c>
</texttable>

<t>Organisations publish independently and may use delegation or federation under
existing trust arrangements. Knowing an organisation's name does not establish
trust. Conversely, a partner's agents and endpoints may be unknown even when
the organisational relationship is established.</t>

<t>DNS and mDNS are possible discovery mechanisms; others may also be suitable.
Protocol work should reuse existing IETF mechanisms where possible.</t>

</section>
<section anchor="scenarios"><name>Example Scenarios</name>

<t>The four scenarios in this section ground the rest of the document. The first
follows a personal assistant coordinating an appointment across an
organisational boundary. The second follows a media orchestration agent
provisioning edge compute within a broadcaster and its cooperating providers.
The third follows the same personal assistant discovering the agents of an
unfamiliar building from the local network it has joined. The fourth
illustrates infrastructure-assisted discovery in a managed enterprise
network. The discovery characteristics, pattern, and categories in the
following sections draw on them.</t>

<section anchor="appointment-coordination"><name>Cross-Organisation Appointment Coordination</name>

<t>Alice asks her AI assistant, Hermes, to review her schedule and arrange lunch
with Bob at another organisation, including a restaurant table for two near
the office. Later, she asks to move both the appointment and the reservation
to a different day.</t>

<t>The example combines capability and resource discovery across an organisational
boundary, then shows how Hermes can reuse what it has learned.</t>

<section anchor="actors-and-assumptions"><name>Actors and Assumptions</name>

<t>Hermes Agent provides the agent harness for Alice's assistant. The running
assistant, called Hermes here, is the discovering entity. Alice talks to it
through a conversational interface. Her calendar service is already configured;
Hermes can read it but cannot change it.</t>

<t>Alice's and Bob's organisations are assumed to cooperate under an established
trust relationship. Their calendar agents have not previously interacted.
Hermes knows Bob's organisation but not its calendar-agent endpoints. Bob's
agent can coordinate appointments and create events, subject to permission.</t>

<t>The restaurant-booking service is assumed to be available through a cooperating
provider with an established trust relationship. OpenTable is used as an
illustrative provider; the example assumes a suitable agent-accessible interface
and does not claim that a particular integration or trust arrangement exists.</t>

<t>Alice is assumed to supply enough context to distinguish the intended Bob.</t>

</section>
<section anchor="initial-discovery-at-a-known-organisation"><name>Initial Discovery at a Known Organisation</name>

<t>Alice asks Hermes to find a time for lunch with Bob on Thursday and book a
table for two near the office. Hermes reads her calendar, then needs to find a
calendar-coordination agent at Bob's organisation. It knows the organisation
and required capability, and may have constraints on the communication
protocol.</t>

<t>Hermes locates the organisation's discovery entry point and queries its
catalogue for calendar-coordination agents. The result identifies candidates
and their contact information. DNS could provide the entry point; the example
does not depend on a particular bootstrap or catalogue protocol.</t>

<t>A candidate may serve the whole organisation or particular users. Hermes needs
to determine whether it can handle the request concerning Bob. The application
then selects a candidate, obtains any necessary authorisation, and exchanges
proposed times. Bob's agent creates the event in his calendar. Hermes still has
no permission to write to Alice's calendar; invitation handling is an
application matter.</t>

</section>
<section anchor="supporting-resource-discovery-and-restaurant-reservation"><name>Supporting Resource Discovery and Restaurant Reservation</name>

<t>Hermes obtains free/busy information through the calendar services. Alice's
calendar was already known, so reading it required no discovery. It discovers
any additional data source it needs before querying that source.</t>

<t>With a suitable time identified, Hermes proceeds as follows:</t>

<t><list style="numbers" type="1">
  <t>Discover the restaurant-booking service through the cooperating provider's
discovery entry point. The result identifies the booking capability and how
to contact it.</t>
  <t>Query the service for restaurants near the office with a table for two at
the proposed time. Availability, price, and booking conditions come from the
service's application interface.</t>
  <t>Present a suitable option to Alice and ask her to confirm the restaurant,
time, and any booking conditions.</t>
  <t>On confirmation, request the reservation through the service and retain its
booking reference. Report whether the reservation succeeded.</t>
</list></t>

<t>The discovery target is the booking service. Restaurant search, table
availability, and reservation are subsequent application activities. The table
is reserved through the service, not through DAWN.</t>

<t>The following exchanges show the restaurant-booking part of the example.
The discovery steps also apply to finding Bob's calendar agent, using his
organisation's discovery entry point instead of the booking provider's.</t>

<figure><artwork><![CDATA[
 Alice            Hermes              Provider's              Booking
                                       discovery              service
   |                 |                     |                     |
   |--Lunch request-->                     |                     |
   |                 |                     |                     |
  Discovery
   |                 |-Booking capability-->                     |
   |                 <-Name, URI, protocol-|                     |
   |                 |                     |                     |
  Application exchange
   |                 |----------Time, area, party size----------->
   |                 <--------Options, price, conditions---------|
   <-Booking option--|                     |                     |
   |-----Confirm----->                     |                     |
   |                 |----------Reserve selected table----------->
   |                 <---------Result, booking reference---------|
   <-Booking result--|                     |                     |
   |                 |                     |                     |
]]></artwork></figure>

</section>
<section anchor="reconnection-and-rediscovery"><name>Reconnection and Rediscovery</name>

<t>Alice asks Hermes to move the lunch to Friday. Hermes has cached discovery
information for both the calendar agent and the booking service, including
their names, endpoints, protocols, and available freshness information. If
these remain usable, it can reconnect without repeating the catalogue queries.</t>

<t>An expired record or changed endpoint may require a refresh. If the agent
cannot be found or no longer offers calendar coordination, Hermes can return
to the organisation's discovery entry point. A temporary connection failure
alone does not establish that the agent has been withdrawn.</t>

<t>The application may also need to retrieve a changed capability card and
reassess the agent. Finding a replacement does not establish that it holds
the original booking or has permission to change it.</t>

<t>Hermes checks Friday's calendar availability and asks the booking service
whether the reservation can be moved. It presents the revised arrangements
and any changed conditions to Alice for confirmation, then requests both
changes through the respective services. If only one succeeds, Hermes reports
the outstanding change to Alice. Discovery does not make the two updates a
single transaction.</t>

<t>The services below are contacted separately. If cached information is still
usable, the discovery exchanges are skipped. Availability checks and booking
changes use application interfaces.</t>

<figure><artwork><![CDATA[
 Alice            Hermes               Discovery           Calendar /
                                     entry points             booking
                                                             services
   |                 |                     |                     |
   |-Move to Friday-->                     |                     |
   |                 |                     |                     |
  Reuse cached discovery information if still valid.
  If refresh or rediscovery is needed:
   |                 |-Name or capability-->                     |
   |                 <---Contact details---|                     |
   |                 |                     |                     |
  Application exchanges with each service
   |                 |--Friday availability / booking reference-->
   |                 <------Options and changed conditions-------|
   <--Revised plan---|                     |                     |
   |-----Confirm----->                     |                     |
   |                 |-----Change appointment / reservation------>
   |                 <-----Separate results for each change------|
   <-----Outcome-----|                     |                     |
   |                 |                     |                     |
]]></artwork></figure>

</section>
<section anchor="discovery-information-needed-in-this-scenario"><name>Discovery Information Needed in This Scenario</name>

<t>The first requests identify an organisation and a capability: calendar
coordination or restaurant booking. Reconnection starts with a known agent or
service. In either case, useful results include:</t>

<t><list style="symbols">
  <t>the entity's name, type, and a service or capability identifier;</t>
  <t>reachability information and supported communication methods; and</t>
  <t>references used to obtain that minimum information through indirection.</t>
</list></t>

<t>The Architecture defines the minimum field set. A reference may lead to
further discovery information or to richer application information. Fetching
a capability card beyond that minimum, detailed policy, live calendar data,
or table availability is outside discovery. Booking references are application
state, separate from cached discovery information.</t>

</section>
<section anchor="security-privacy-and-operational-considerations"><name>Security, Privacy, and Operational Considerations</name>

<t>All cross-organisation discovery information is integrity-protected under the
assumed trust arrangements, including information obtained through references.
Hermes checks its origin and freshness. An authentic publication does not prove
that an agent may act for Bob. A version comparison can reveal change, but
does not establish authenticity.</t>

<t>The discovery query may reveal Alice's interest in Bob's organisation and its
scheduling service. Calendar contents and personal details can be restricted
to the subsequent authorised exchange. Discovery records may also need access
controls.</t>

<t>For troubleshooting, operators may need to know which source Hermes used,
whether it used cached information, and why it repeated discovery. Logs can
record
these decisions, subject to privacy and retention controls.</t>

</section>
</section>
<section anchor="personalised-live-media"><name>Provisioning Edge Compute for Personalised Live Media</name>

<t>A broadcaster offers a personalised live programme [object-based media
delivery]. Viewers may choose different audio, graphics, or accessibility
features. Some devices cannot combine these media objects themselves, so
nearby edge compute renders part or all of the programme for them.</t>

<t>Before the broadcast, an operator asks a media orchestration agent to arrange
enough compute for the expected audience, balancing delay, cost, and energy
use. The agent needs to find the services and information sources that can
help it do this.</t>

<section anchor="actors-and-assumptions-1"><name>Actors and Assumptions</name>

<t>The media orchestration agent coordinates the request. A compute allocation
agent arranges resources at suitable sites, using an optimisation tool to
compare options. Data services provide audience forecasts and information
about compute and network conditions.</t>

<t>These entities operate within the broadcaster's organisation or cooperating
providers with established trust relationships. The discovery entry points are
known, but individual service endpoints may not be.</t>

<t><eref target="https://agenticresourcediscovery.org/">Agentic Resource Discovery (ARD)</eref>
is a possible interface to a provider's catalogue in this scenario. It
provides a common way to describe and search agents, tools, and services.
A provider could expose its compute allocation and telemetry services through
ARD, allowing the media agent to find candidates without preconfiguring every
service endpoint or loading every service description into its context. Here,
queries would be limited to the organisation or cooperating providers. ARD is
an illustrative option; protocol choice remains open. Resource allocation and
invocation continue through the service's own interfaces.</t>

</section>
<section anchor="discovery-and-provisioning"><name>Discovery and Provisioning</name>

<t><list style="numbers" type="1">
  <t>The media agent queries the relevant discovery entry points for a compute
allocation capability and any required data services. Results identify the
entities and how to contact them.</t>
  <t>The allocation agent discovers suitable site controllers and
media-processing services, including GPU rendering where needed. It obtains
their names, service identifiers, endpoints, and supported communication
methods.</t>
  <t>Through the services' application interfaces, the agents obtain audience
forecasts, current capacity, and cost, energy, and delay estimates. The
optimisation tool uses these inputs and the operator's priorities to
propose a placement.</t>
  <t>Subject to the operator's policy and authorisation, the allocation agent
requests provisioning through the site controllers. It reports the result,
or explains why the available resources cannot meet the request.</t>
</list></t>

<t>The diagram summarises discovery and the later application exchanges. The
agents contact each service separately.</t>

<figure><artwork><![CDATA[
 Media / allocation       Discovery             Data services /
 agents                  entry points          site controllers
   |                          |                       |
   |--Required capability---->|                       |
   |<--Name, URI, protocol----|                       |
   |                          |                       |
   |--Forecast / resource information request-------->|
   |<--Demand, capacity, cost, energy, delay----------|
   |                                                  |
   |  Compare options using the optimisation tool     |
   |                                                  |
   |--Provision selected resources------------------->|
   |<--Result / resource references-------------------|
]]></artwork></figure>

<t>Discovery provides the information needed to contact an entity. Comparing
sites, reserving compute, steering traffic, and delivering media are
application activities outside DAWN.</t>

</section>
<section anchor="changes-during-the-broadcast"><name>Changes During the Broadcast</name>

<t>Audience demand or site availability may change. The agents can reuse valid
discovery information and query current conditions through the data services.
Changed or expired discovery records may require a refresh or a new query.
Moving workloads or adding capacity remains an application decision.</t>

</section>
<section anchor="security-and-privacy"><name>Security and Privacy</name>

<t>Discovery information is integrity-protected, including across provider
boundaries, and its origin and freshness are checked. Finding a controller
does not grant permission to provision resources. Viewer details and detailed
capacity data are restricted to authorised application exchanges.</t>

</section>
</section>
<section anchor="visitor-assistance"><name>Visitor Assistance in an Unfamiliar Building</name>

<t>Alice visits Bob's office for a meeting. The building is shared by several
organisations and run by a facilities operator. On arrival, she joins the
building's guest Wi-Fi network and asks Hermes to check her in and show her the
way to the meeting room.</t>

<t>The example shows discovery that starts from the network a client has joined,
rather than from a name. The same applies to visitors at a conference venue,
hotel, hospital, airport, or stadium.</t>

<section anchor="actors-and-assumptions-2"><name>Actors and Assumptions</name>

<t>Hermes, Alice's assistant from <xref target="appointment-coordination"/>, runs on her phone
and is the discovering entity. The facilities operator runs a reception agent,
which checks visitors in and notifies their hosts, and a wayfinding agent,
which gives directions inside the building. Both are advertised on the guest
network.</t>

<t>Hermes knows neither the operator's name nor any catalogue it publishes, and
has no prior relationship with it. The operator's agents are not published at
the discovery entry point of Bob's organisation. The network Alice has joined
is the only starting point Hermes has.</t>

<t>Joining the network is outside discovery. Using the discovered agents remains
subject to application permissions.</t>

</section>
<section anchor="discovery-from-the-joined-network"><name>Discovery from the Joined Network</name>

<t>With Alice's phone attached to the guest network, Hermes proceeds as follows:</t>

<t><list style="numbers" type="1">
  <t>Request the agents advertised on the network it has joined. The request
names no organisation, entity, or capability: the network bounds it, as the
organisation's discovery entry point bounds the requests in
<xref target="appointment-coordination"/>. DNS-based Service Discovery over multicast DNS
could provide this; the example does not depend on a particular discovery
protocol.</t>
  <t>Receive, for each advertised agent, its name, its communication protocol,
and how to contact it, possibly with a reference to a richer description.
The names, such as "Reception" and "Wayfinding", are meant to be read by
people. An agent may support more than one protocol, for example A2A and
MCP, in which case Hermes uses one that it supports.</t>
  <t>Present the names to Alice, who picks the agents to use. Alternatively,
Hermes can retrieve the referenced descriptions and decide which agents fit
her request. Either way, the choice is made after discovery.</t>
  <t>Check Alice in through the reception agent, which notifies Bob, then ask
the wayfinding agent for directions to the meeting room.</t>
</list></t>

<t>The discovery target is the set of agents the building advertises. Choosing
among them, checking in, and finding the way are subsequent application
activities. To notify Bob, the reception agent may itself discover an agent at
the discovery entry point of his organisation, as in
<xref target="appointment-coordination"/>.</t>

<figure><artwork><![CDATA[
 Alice            Hermes              Building's          Reception /
                                     guest network         wayfinding
                                                              agents
   |                 |                     |                     |
   |---Check me in--->                     |                     |
   |                 |                     |                     |
  Discovery within the joined network
   |                 |--Advertised agents-->                     |
   |                 <-Name, URI, protocol-|                     |
   |                 |                     |                     |
   <---Agent names---|                     |                     |
   |---Pick agents--->                     |                     |
   |                 |                     |                     |
  Application exchanges with each agent
   |                 |--------------Check in Alice--------------->
   |                 <---------Checked in, host notified---------|
   |                 |-----------Route to meeting room----------->
   |                 <----------------Directions-----------------|
   <---Directions----|                     |                     |
   |                 |                     |                     |
]]></artwork></figure>

</section>
<section anchor="changes-during-the-visit"><name>Changes During the Visit</name>

<t>While Alice is in the building, Hermes can reuse the discovery information it
has obtained. Agents may appear or be withdrawn during her visit; an agent that
serves a single event, for example, is withdrawn when the event ends. A changed
or withdrawn agent may require a refresh or a new request.</t>

<t>The information applies only to the network on which it was obtained. When
Alice leaves the building, Hermes stops relying on it; at another building it
discovers again. If Alice returns the next day, Hermes cannot assume that the
same agents are still advertised.</t>

<t>In a large building or campus, the guest network may span several network
segments. Alice expects the same agents to be discoverable wherever she is
attached, so the operator may make the same discovery information available
across those segments. How it does so is a deployment matter.</t>

<t>The operator also decides which agents are visible on which network. Agents
for staff, such as building-control agents, are not advertised on the guest
network.</t>

</section>
<section anchor="discovery-information-needed-in-this-scenario-1"><name>Discovery Information Needed in This Scenario</name>

<t>The request identifies no organisation, entity, or capability; the joined
network bounds it. As in <xref target="appointment-coordination"/>, useful results include
the entity's name, reachability information and supported communication
methods, and references used to obtain further information. The starting point
differs, but discovery on a local network adds no fields to the minimum
discovery information.</t>

<t>Names are most useful when they are meaningful to people, because Alice may
choose among the agents directly. Evaluating what an agent can do, beyond the
minimum discovery information, is outside discovery.</t>

</section>
<section anchor="security-and-privacy-1"><name>Security and Privacy</name>

<t>Like a well-run enterprise network, the building's network can offer some
protection against rogue advertisements. The operator can isolate guest devices
from one another, or accept advertisements on the guest network only from its
own infrastructure, so that another visitor cannot advertise an agent named
"Reception". These measures complement integrity protection and an origin check
of the discovery information, as in the other scenarios, but do not replace
them: not every network is run this way, and locality alone does not establish
trust.</t>

<t>An authentic advertisement does not entitle an agent to Alice's personal
details. Checking in shares her name and Bob's with the operator, in an
application exchange that Alice authorises.</t>

<t>A request bounded by the joined network names no organisation or capability,
so it reveals little about Alice's intent, although other devices on the
network may observe it. Advertisements on the guest network are visible to
every visitor, so the operator publishes there only what all visitors may see,
without exposing its internal structure or its tenants.</t>

</section>
</section>
<section anchor="infrastructure-assisted-managed-enterprise"><name>Infrastructure-Assisted Discovery in a Managed Enterprise Network</name>

<t>An enterprise operates multiple campuses and edge-compute sites. Field engineers
use an AI Operations Assistant to diagnose equipment and network problems.
Troubleshooting Agents may be deployed at site, regional-edge, or shared-cloud
locations.</t>

<t>The Operations Assistant may need to obtain the information required to connect
to an identified Troubleshooting Agent or troubleshooting service. In a managed
deployment, some information useful to discovery may already be available from
enterprise infrastructure. For example, hosting infrastructure may know the
resource's current endpoint and communication protocol, while network
infrastructure may know the requester's current site, tenant, VPN, edge region,
or other deployment context.</t>

<t>This infrastructure-provided information may contribute to the minimum
discovery information used by the discovery mechanism. How the information is
obtained,
maintained, or supplied is deployment-specific and outside the scope of this
scenario.</t>

<section anchor="infra-assisted-actors"><name>Actors and Assumptions</name>

<t>The Operations Assistant is the discovering entity used by the field engineer.
A Troubleshooting Agent or troubleshooting service is the discoverable entity.</t>

<t>The enterprise hosting environment maintains current discovery-relevant
information about the resource, such as its identifier, externally reachable
endpoint, and supported communication protocol.</t>

<t>The enterprise network also has information about the Operations Assistant's
current administrative or network context, such as site, tenant, VPN, network
slice, or edge region. The Operations Assistant does not need to understand or
explicitly signal these infrastructure-specific details. Where useful, an
abstract representation of this context may form part of the minimum
discovery information.</t>

<t>These forms of infrastructure assistance correspond to the Resource State Hook
and Attachment Context Hook described in
<xref target="I-D.dunbar-dawn-infra-assisted-discovery"/>. Resource registration,
deployment-state maintenance, network-context derivation, and enterprise-policy
configuration are outside the scope of this scenario.</t>

</section>
<section anchor="infra-assisted-discovery-use"><name>Discovery and Use of the Troubleshooting Agent</name>

<t>An engineer at Site A asks the Operations Assistant to diagnose a problem.</t>

<t>An application or enterprise function identifies the Troubleshooting Agent or
service to be contacted. DAWN discovery is then used to obtain the minimum
information needed to connect to that resource.</t>

<t>For example, the discovery input may identify:</t>

<figure><artwork><![CDATA[
   Troubleshooting-Agent.Site-A
]]></artwork></figure>

<t>At the same time, infrastructure may have requester context such as:</t>

<figure><artwork><![CDATA[
   Site A
   Engineering VPN
   Operations tenant
]]></artwork></figure>

<t>and current resource state such as:</t>

<figure><artwork><![CDATA[
   Endpoint: https://troubleshoot-a.example
   Protocol: A2A
]]></artwork></figure>

<t>Requester context may help determine the appropriate discovery domain, resolver
view, local discovery scope, or bootstrap entry point. Current resource state may
help ensure that the returned endpoint and protocol information are current.</t>

<t>Conceptually:</t>

<figure><artwork><![CDATA[
              Resource State Hook
                      |
                      v
Requester -----> DAWN Discovery -----> Discovery Information
                      ^
                      |
              Attachment Context Hook
]]></artwork></figure>

<t>The requester context is used to assist bootstrap discovery; it is not used by
DAWN to compare or select among Troubleshooting Agents. Resource identification,
capability evaluation, selection, authorisation, diagnosis, telemetry access, and
remediation occur outside the DAWN discovery process.</t>

<t>The same model applies to remote troubleshooting. An engineer attached at Site A
may be troubleshooting equipment at Site B. An application or enterprise
function identifies the relevant Site-B resource, while DAWN obtains the
information needed to connect to it. The requester's Site-A context may still
help determine the appropriate discovery domain or resolver view.</t>

</section>
<section anchor="infra-assisted-changes"><name>Changes in Attachment or Deployment</name>

<t>Requester context and resource state may change independently.</t>

<t>If the engineer moves from Site A to Site B, a subsequent discovery may use a
different discovery domain, resolver view, local discovery scope, or bootstrap
entry point.</t>

<t>Similarly, a Troubleshooting Agent may move to another hosting environment or
receive a new externally reachable endpoint while retaining the same logical
identity.</t>

<t>Infrastructure-assisted discovery allows subsequent discovery to use current
requester context and resource state without requiring the Operations Assistant
to understand how the underlying deployment changed.</t>

<t>How mobility, reassociation, endpoint changes, or policy mappings are detected
and maintained is outside DAWN.</t>

</section>
<section anchor="infra-assisted-security-privacy"><name>Security and Privacy</name>

<t>Infrastructure-provided information used for discovery needs appropriate
integrity, origin, and freshness protection.</t>

<t>Requester context may be derived from enterprise-sensitive information such as
tenant identifiers, VPNs, network slices, edge locations, or internal topology.
An abstract requester context can allow these details to remain hidden from the
discovering entity and avoid encoding them directly in the discovery request.</t>

<t>Infrastructure assistance does not authorise use of the discovered AI resource
or access to enterprise systems. Authentication, authorisation, trust evaluation,
and subsequent interaction occur after discovery.</t>

</section>
</section>
</section>
<section anchor="discovery-characteristics"><name>Discovery Characteristics</name>

<t>The scenarios in <xref target="scenarios"/> share a common question: what must a client
discover before it can attempt interaction with an entity? The following
characteristics are drawn from them.</t>

<t><list style="symbols">
  <t>Discovery may be initiated by autonomous software or by a human operator.
Alice's assistant discovers on her behalf in <xref target="appointment-coordination"/>;
an operator's request leads agents to discover further services in
<xref target="personalised-live-media"/>.</t>
  <t>The discovered target may be a specific named entity or a set of entities
determined by properties or classification. The assistant first looks for a
calendar-coordination capability at a known organisation, and later
reconnects to the specific agent it found. In
<xref target="infrastructure-assisted-managed-enterprise"/>, the target is an already
identified Troubleshooting Agent.</t>
  <t>The starting point of discovery varies: an organisation's name in
<xref target="appointment-coordination"/>, known discovery entry points in
<xref target="personalised-live-media"/>, and only the network the client has joined in
<xref target="visitor-assistance"/>. The minimum discovery information returned is the
same in each case. In <xref target="infrastructure-assisted-managed-enterprise"/>,
enterprise infrastructure helps determine the starting point from the
requester's attachment context.</t>
  <t>Capability is often an important discovery input, but it is not the only one.
Organisation, jurisdiction, locality, protocol, policy, and responsible party
also appear in several use cases.</t>
  <t>The minimum discovery information may change over time. Freshness and caching
therefore matter even when detailed runtime properties are obtained later
through application interaction. The scenarios reuse cached discovery
information and refresh it when it has expired or changed, while calendar
contents, table availability, and site capacity are obtained from the
services themselves.</t>
  <t>Discovery may need to account for entities that are dynamic, mobile, or
available only in a particular context. Agents are advertised and
withdrawn during a visit in <xref target="visitor-assistance"/>; the engineer and the
Troubleshooting Agent may each move in
<xref target="infrastructure-assisted-managed-enterprise"/>.</t>
  <t>Trust in discovery information is different from trust in the discovered
entity. A discovery mechanism can help protect discovery metadata, but it
does not decide whether the discovered entity should be used. An authentic
record for a calendar agent does not show that the agent may act for Bob,
and finding a site controller does not grant permission to provision
resources.</t>
  <t>Brokers and aggregators may serve an organisation or cooperating group.
Discovery supports independent publication rather than requiring a single
central registry or an index of resources across the wider Internet.</t>
</list></t>

</section>
<section anchor="discovery-pattern"><name>Discovery Pattern</name>

<t>The scenarios in <xref target="scenarios"/> follow a common pattern.</t>

<t><list style="numbers" type="1">
  <t>A discovering entity has a task, intent, policy requirement, or operational
need.</t>
  <t>The discovering entity needs to find an entity, or class of entities, that
can satisfy that need.</t>
  <t>The discovering entity forms a discovery request using information such as
a name, organisation, entity type, capability, location, jurisdiction,
communication protocol, or policy constraint.</t>
  <t>The discovery mechanism returns information about one or more candidate
entities.</t>
  <t>The discovering entity uses that information to decide whether selection,
authorisation, capability exchange, or communication should be attempted.</t>
</list></t>

<t>The last step is outside the scope of discovery. However, discovery has to
return enough information for this step to be possible.</t>

<t>In <xref target="appointment-coordination"/>, Alice's lunch request creates the need
(step 1) for a calendar-coordination agent at Bob's organisation (step 2).
The assistant queries that organisation's discovery entry point by capability
(step 3) and receives candidates with their contact information (step 4).
Choosing a candidate, obtaining authorisation, and exchanging proposed times
are step 5. In <xref target="personalised-live-media"/>, the same steps are repeated for
the compute allocation capability, the data services, and the site
controllers. In <xref target="visitor-assistance"/>, the request in step 3 names no
organisation, entity, or capability: the network the assistant has joined
bounds it. In <xref target="infrastructure-assisted-managed-enterprise"/>, the request in
step 3 names an identified resource, and infrastructure-provided requester
context helps determine the discovery domain or entry point used.</t>

<t>The Architecture determines which query properties belong in minimum discovery
information. Other constraints are evaluated by the application.</t>

<t>Discovery may take several steps. A client may follow a reference, refresh a
cached result, or repeat a query when the information is no longer sufficient.</t>

</section>
<section anchor="categories-of-discovery"><name>Categories of Discovery</name>

<t>The categories generalise the scenarios in <xref target="scenarios"/>. Each category
includes assumptions, discovery impacts, and examples within the settings in
<xref target="applicability"/>.</t>

<section anchor="capability-oriented-discovery"><name>Capability-Oriented Discovery</name>

<t>A client needs to find an entity that provides a particular function or
capability, such as an agent, tool, task, service, or model-serving endpoint.</t>

<section anchor="assumptions"><name>Assumptions</name>

<t>The client can express the required function using the discovery properties
supported by the architecture. A service type or capability identifier may be
sufficient. The result identifies the function and how to reach the entity,
and may include a reference to a capability card.</t>

</section>
<section anchor="discovery-impacts"><name>Discovery Impacts</name>

<t>Capability-oriented discovery suggests support for discovery by function,
capability, skill, entity type, and protocol. The returned discovery information
needs to include enough information to allow later selection, authorisation,
capability exchange, or communication to be attempted.</t>

</section>
<section anchor="examples"><name>Examples</name>

<t>A scheduling assistant needs to find a calendar-coordination agent at a
partner organisation and learn how to contact it. This is the scenario in
<xref target="appointment-coordination"/>.</t>

<t>An agentic workflow decomposes a user request into several subtasks. The
workflow needs to discover agents, tools, services, or tasks that can
participate in the work. Discovery provides candidate entities and their
published properties; the workflow then performs selection and orchestration
outside DAWN.</t>

</section>
</section>
<section anchor="resource-oriented-discovery"><name>Resource-Oriented Discovery</name>

<t>A client needs to discover resources supporting an AI system, such as data
sources, knowledge bases, models, inference services, or compute services.</t>

<section anchor="assumptions-1"><name>Assumptions</name>

<t>This discovery category assumes that the discovered resource may have
properties that are partly static and partly dynamic. For example, a dataset
description may be relatively stable, while freshness or access policy may
change. A compute resource may have stable hardware properties but rapidly
changing availability, load, price, or locality.</t>

<t>It also assumes that some discovery information may be sensitive. Data
classification, model provenance, jurisdiction, permitted use, and operational
capacity may need visibility controls.</t>

</section>
<section anchor="discovery-impacts-1"><name>Discovery Impacts</name>

<t>Discovery returns the minimum information needed to locate and contact the
resource. It may return a pointer to an application service for current state,
detailed policy, or authorisation. Accessing an already known data source to
read its contents is an application query, not resource discovery.</t>

<t>Properties such as jurisdiction, format, freshness, and access method may
motivate discovery requirements. The Architecture work determines which belong
in the minimum discovery information. Richer descriptions, live availability,
and detailed policy information are obtained outside the discovery process.</t>

</section>
<section anchor="examples-1"><name>Examples</name>

<t>An enterprise agent needs to find a data source for retrieval-augmented
generation. Discovery identifies a relevant internal source and how to contact
it. The application subsequently checks detailed freshness, format, and access
conditions and retrieves data through the source's native interface.</t>

<t>A scheduler for an AI workload needs to find a compute service within its
organisation or a cooperating provider. Discovery identifies the service and
its contact information. Checking accelerator availability, jurisdictional
constraints, and allocation policy can require subsequent application queries.
The scenario in <xref target="personalised-live-media"/> is an instance of this example.</t>

<t>An AI application needs to find an inference service for a particular modality.
Discovery supplies the relevant service type and communication information.
Detailed model provenance, safety classification, and permitted use are assessed
outside discovery where they exceed the minimum information.</t>

<t>A user or agent needs to discover a model-serving resource for inference.
Discovery supplies its function and access method; subsequent interaction
obtains richer model information when needed.</t>

</section>
</section>
<section anchor="administrative-scope-extensions"><name>Administrative Scope Extensions</name>

<t>Discovery crosses organisational, administrative, or tenancy boundaries.
A client may need to find a partner's resource, or a provider may expose
different discovery views to its tenants, customers, or departments.</t>

<section anchor="assumptions-2"><name>Assumptions</name>

<t>Organisations control what they publish and who can see it. Cooperation and
authority to act for a user rely on existing arrangements. Discovery information
may identify the publishing domain or responsible party to support later checks.</t>

</section>
<section anchor="discovery-impacts-2"><name>Discovery Impacts</name>

<t>DAWN discovery needs to support discovery across administrative domains without
requiring a single central registry. It also needs to support scoped discovery
where the information returned depends on tenant, customer, department, network,
or policy context.</t>

<t>Publication scope helps the client interpret a result. Discovery must also
avoid exposing sensitive tenant or organisational structure to unauthorised
parties.</t>

</section>
<section anchor="examples-2"><name>Examples</name>

<t>An enterprise agent acting for an employee needs to discover an agent at a
cooperating supplier. The discovery result indicates how to contact the
supplier's agent and provides information needed by later authorisation and
policy checks.</t>

<t>A software-as-a-service provider hosts agents or tools for multiple customers.
Each customer needs discovery information scoped to its own tenancy. The same
provider may also need different discovery views for internal operators and
cooperating customers.</t>

<t>A research consortium operates AI services across several cooperating
institutions with established trust relationships. Each institution publishes
information about its own agents, data services, and tools. Collaborators need
to discover entities by capability while respecting institutional boundaries
and trust models.</t>

</section>
</section>
<section anchor="operational-discovery"><name>Operational Discovery</name>

<t>A human operator, management system, or AI operations agent needs to locate
AI resources and supporting tools for troubleshooting, audit, incident response,
or compliance review.</t>

<section anchor="assumptions-3"><name>Assumptions</name>

<t>This discovery category assumes that discovery is useful for both autonomous
systems and human-operated tools. It also assumes that operational environments
may be multi-vendor, multi-domain, and partly private.</t>

<t>Operational discovery needs to identify relevant resources and how to contact
them. An operational client may subsequently obtain detailed runtime state,
observability data, or compliance information. Those exchanges are outside
discovery and may require separate permissions.</t>

</section>
<section anchor="discovery-impacts-3"><name>Discovery Impacts</name>

<t>DAWN discovery may need to support tooling and operational inspection, not only
agent-to-agent workflows. Discovery metadata may need to be logged, auditable,
and understandable by operators.</t>

<t>Management and diagnostics for the discovery system itself may also be needed
so that operators can understand discovery behaviour and failures.</t>

<t>Brokers, directory services, and operational tools may themselves be discovery
targets when they support an AI system.</t>

<t>Observability of the discovery process is a separate operational consideration.
Recording a discovery result or logging a later action does not itself
constitute discovery of an operational resource.</t>

</section>
<section anchor="examples-3"><name>Examples</name>

<t>A human operator needs to locate the AI agents maintained by a team within an
organisation. Discovery provides their service types and communication
information. Inspection of their runtime behaviour occurs subsequently.</t>

<t>An AI-assisted network operations system needs to discover telemetry sources,
topology systems, control points, and remediation tools within an organisation
or cooperating group. DAWN can help identify these supporting AI resources and
their communication methods. Diagnosis, correlation, action recommendation,
and remediation remain outside discovery. The managed-enterprise scenario in
<xref target="infrastructure-assisted-managed-enterprise"/> illustrates how
infrastructure-provided resource state and requester context can assist this
bootstrap discovery.</t>

<t>An edge deployment includes lightweight agents that need fast and cacheable
discovery because local connectivity is constrained. Discovery provides enough
stable information for connection bootstrapping while avoiding reliance on
rapidly changing operational state.</t>

</section>
</section>
</section>
<section anchor="classes-of-use-case"><name>Classes of Use Case</name>

<t>The taxonomy in <xref target="I-D.akhavain-moussa-dawn-problem-statement"/> provides
background for classifying AI resources and their supporting entities.</t>

<section anchor="ai-agent"><name>AI Agent</name>

<t>TBD</t>

</section>
<section anchor="software-service"><name>Software Service</name>

<t>TBD</t>

</section>
<section anchor="compute-workload"><name>Compute Workload</name>

<t>TBD</t>

</section>
<section anchor="network-function"><name>Network Function</name>

<t>TBD</t>

</section>
<section anchor="application-endpoint"><name>Application Endpoint</name>

<t>TBD</t>

</section>
</section>
<section anchor="security-considerations"><name>Security Considerations</name>

<t>The use cases in this document involve discovery information that may affect
which entity is contacted, what protocol is used, and what trust indicators are
presented. Incorrect or malicious discovery information could cause a
discovering entity to contact the wrong entity, disclose information to an
attacker, or use an unsuitable service.</t>

<t>Outside a local network, all discovery information exchanged between DAWN
participants requires integrity protection. Local deployments may also provide
such protection. Where it is absent, the deployment needs to account for the
risks of unprotected discovery information; locality alone does not establish
trust.</t>

<t>Discovery mechanisms also need to address authenticity, freshness, and access
controls using established security mechanisms and trust arrangements. A
cached digest or version comparison detects change but does not independently
authenticate discovery content. This document does not select a protection
mechanism or define new trust-evaluation methods.</t>

<t>Security of discovery metadata is distinct from trust in the discovered entity.
Authentication, authorisation, attestation, and policy checks for later
interaction are outside discovery.</t>

<t>Identity management and establishing trust relationships are also outside
DAWN's initial scope; an authentic publication does not establish authority to
act for a particular person.</t>

</section>
<section anchor="privacy-considerations"><name>Privacy Considerations</name>

<t>Discovery queries may reveal information about the intent, capability needs, or
operational state of the discovering entity. Published discovery information may
also reveal information about deployed services, agents, data sources, models,
or organisational relationships.</t>

<t>This suggests that a DAWN discovery mechanism will need to consider what
information is public, what information is restricted, and what information
should not be exposed through discovery.</t>

<t>Privacy-sensitive information can include proprietary capabilities, deployment
location, capacity, runtime state, model or dataset metadata, requester
identity, search history, and query intent.</t>

</section>
<section anchor="operational-considerations"><name>Operational Considerations</name>

<t>Enterprise, cloud, and edge deployments have different needs for publication,
caching, freshness, authorisation, observability, and operational control.</t>

<t>Dynamic information such as current load, availability, price, or status may
change too frequently to be carried directly in a general discovery mechanism.
Such application state can be obtained outside discovery through a referenced
service. The minimum discovery information has its own freshness needs: an
endpoint or supported protocol may also change.</t>

<t>A client may refresh retained information or repeat discovery when it is no
longer sufficient. A changed description need not imply a different entity, and
a temporary communication failure need not imply withdrawal. Recovery of
application state or transfer of an existing task to a replacement is outside
discovery.</t>

<t>Across administrative domains, operational considerations include publication
authority, caching, freshness, visibility controls, logging, abuse handling, and
failure behaviour.</t>

</section>
<section anchor="iana-considerations"><name>IANA Considerations</name>

<t>This document has no IANA actions.</t>

</section>


  </middle>

  <back>


<references title='References' anchor="sec-combined-references">

    <references title='Normative References' anchor="sec-normative-references">




<reference anchor="I-D.farrel-dawn-terminology">
   <front>
      <title>Terminology for the Discovery of Agents With Names (DAWN)</title>
      <author fullname="Adrian Farrel" initials="A." surname="Farrel">
         <organization>Old Dog Consulting</organization>
      </author>
      <author fullname="Kehan Yao" initials="K." surname="Yao">
         <organization>China Mobile</organization>
      </author>
      <author fullname="Roland Schott" initials="R." surname="Schott">
         <organization>Deutsche Telekom</organization>
      </author>
      <author fullname="Nic Williams" initials="N." surname="Williams">
         <organization>Infoblox</organization>
      </author>
      <date day="2" month="November" year="2026"/>
      <abstract>
	 <t>   The proliferation of distributed Artificial Intelligence (AI) systems
   and agents has created a need for interoperable mechanisms for
   components of AI systems to discover each other.

   This document defines terminology for Discovery of Agents With Names
   (DAWN), focusing on the terms necessary to describe the discovery of
   information about AI systems and resources (e.g., AI agents).  The
   intention is that this common set of terms can be used by other
   documents related to DAWN and so achieve consistency of meaning
   across the space.

	 </t>
      </abstract>
   </front>
   <seriesInfo name="Internet-Draft" value="draft-farrel-dawn-terminology-07"/>
   
</reference>



    </references>

    <references title='Informative References' anchor="sec-informative-references">




<reference anchor="I-D.akhavain-moussa-dawn-problem-statement">
   <front>
      <title>Problem Statement for the Discovery of Agents, Workloads, and Named Entities (DAWN)</title>
      <author fullname="Arashmid Akhavain" initials="A." surname="Akhavain">
         <organization>Huawei Technologies Canada</organization>
      </author>
      <author fullname="Hesham Moussa" initials="H." surname="Moussa">
         <organization>Huawei Technologies Canada</organization>
      </author>
      <author fullname="Daniel King" initials="D." surname="King">
         <organization>Old Dog Consulting</organization>
      </author>
      <date day="19" month="July" year="2026"/>
      <abstract>
	 <t>   Interacting entities such as agents, tasks, users, workloads, data,
   compute, etc., in AI ecosystem/network are proliferating, yet there
   is no standardised way to discover what entities exist, what
   attributes such as skills, capabilities, physical characteristics,
   etc., they posses, what services they offer, or how to reach them
   across organisational boundaries.

   Discovery today relies on proprietary directories or manual
   configuration, creating fragmented ecosystems that prevent cross-
   domain collaboration.

   This document describes the problem space that motivates Discovery of
   Agents, Workloads, and Named Entities (DAWN).  It clarifies the scope
   of work within entity ecosystems, identifies why current approaches
   are insufficient, and outlines the challenges a standardised
   discovery mechanism must address.  It does not propose a specific
   solution or protocol.

	 </t>
      </abstract>
   </front>
   <seriesInfo name="Internet-Draft" value="draft-akhavain-moussa-dawn-problem-statement-05"/>
   
</reference>

<reference anchor="I-D.king-dawn-requirements">
   <front>
      <title>Requirements for the Discovery of Agents With Names (DAWN)</title>
      <author fullname="Daniel King" initials="D." surname="King">
         <organization>Old Dog Consulting</organization>
      </author>
      <author fullname="Adrian Farrel" initials="A." surname="Farrel">
         <organization>Old Dog Consulting</organization>
      </author>
      <date day="19" month="October" year="2026"/>
      <abstract>
	 <t>   The proliferation of distributed systems, Artificial Intelligence
   (AI) agents, and network services has created a need for
   interoperable mechanisms to discover entities across administrative
   and network boundaries.  Entities may include AI agents, software
   services, and other named resources that need to be found and
   characterised before interaction can begin.

   This document defines the requirements for Discovery of Agents With
   Names (DAWN) and sets out the objectives that a discovery mechanism
   for such entities must satisfy.  It describes what information must
   be discoverable, what properties a discovery mechanism needs to
   support, and what constraints apply to discovery in decentralised
   environments.

   This document does not specify any particular discovery protocol or
   solution.

	 </t>
      </abstract>
   </front>
   <seriesInfo name="Internet-Draft" value="draft-king-dawn-requirements-02"/>
   
</reference>

<reference anchor="I-D.mozley-aidiscovery">
   <front>
      <title>AI Agent Discovery (AID) Problem Statement</title>
      <author fullname="Jim Mozley" initials="J." surname="Mozley">
         <organization>Infoblox, Inc.</organization>
      </author>
      <author fullname="Nic Williams" initials="N." surname="Williams">
         <organization>Infoblox, Inc.</organization>
      </author>
      <author fullname="Behcet Sarikaya" initials="B." surname="Sarikaya">
         <organization>Unaffiliated</organization>
      </author>
      <author fullname="Roland Schott" initials="R." surname="Schott">
         <organization>Deutsche Telekom</organization>
      </author>
      <date day="16" month="April" year="2026"/>
      <abstract>
	 <t>   With the proliferation of AI agents comes a need for mechanisms to
   support agent-to-agent discovery.  This document discusses the scope,
   requirements and considerations to support discovery processes so
   that these are not reliant on manually defined configurations and
   relationships.

	 </t>
      </abstract>
   </front>
   <seriesInfo name="Internet-Draft" value="draft-mozley-aidiscovery-01"/>
   
</reference>

<reference anchor="I-D.agentic-ai-usecases-requirements">
   <front>
      <title>Agentic AI Use Cases and Requirements</title>
      <author fullname="Tirumaleswar Reddy.K" initials="T." surname="Reddy.K">
         <organization>Nokia</organization>
      </author>
      <author fullname="Zaheduzzaman Sarker" initials="Z." surname="Sarker">
         <organization>Nokia</organization>
      </author>
      <author fullname="Kehan Yao" initials="K." surname="Yao">
         <organization>China Mobile</organization>
      </author>
      <date day="2" month="November" year="2026"/>
      <abstract>
	 <t>   This document describes use cases for agentic AI communication
   systems and derives protocol requirements from those use cases.  The
   requirements are intended to guide IETF standardization work on
   protocols in the context of agent-to-agent communication, agent-to-
   tool communication, with focus on dialog management, transport,
   multimodal communication, communication security, agent identity and
   authentication.

	 </t>
      </abstract>
   </front>
   <seriesInfo name="Internet-Draft" value="draft-agentic-ai-usecases-requirements-07"/>
   
</reference>

<reference anchor="I-D.scrm-aiproto-usecases">
   <front>
      <title>Taxonomy for Agentic AI Use Cases</title>
      <author fullname="Roland Schott" initials="R." surname="Schott">
         <organization>Deutsche Telekom</organization>
      </author>
      <author fullname="Julien Maisonneuve" initials="J." surname="Maisonneuve">
         <organization>Nokia</organization>
      </author>
      <author fullname="Luis M. Contreras" initials="L. M." surname="Contreras">
         <organization>Telefonica</organization>
      </author>
      <author fullname="Jordi Ros-Giralt" initials="J." surname="Ros-Giralt">
         <organization>Qualcomm Europe, Inc.</organization>
      </author>
      <date day="4" month="July" year="2026"/>
      <abstract>
	 <t>   Agentic AI systems rely on large language models to plan and execute
   multi-step tasks by interacting with tools and collaborating with
   other agents, creating new demands on Internet protocols for
   interoperability, scalability, and safe operation across
   administrative domains.  This document defines a taxonomy for
   classifying Agentic AI use cases according to the functional protocol
   domains they exercise, such as transport, security and trust,
   discovery, identity, coordination and orchestration, data and context
   management, and operations and management.  The taxonomy is intended
   to give the IETF a structured vocabulary for describing and comparing
   use cases, for identifying which protocol areas require
   standardization attention, and for mapping use case requirements to
   relevant IETF working groups.

	 </t>
      </abstract>
   </front>
   <seriesInfo name="Internet-Draft" value="draft-scrm-aiproto-usecases-05"/>
   
</reference>

<reference anchor="I-D.dunbar-dawn-infra-assisted-discovery">
   <front>
      <title>Infrastructure-Assisted Discovery for AI Agents</title>
      <author fullname="Linda Dunbar" initials="L." surname="Dunbar">
         <organization>Futurewei</organization>
      </author>
      <author fullname="Bin Zhang" initials="B." surname="Zhang">
         <organization>Pengcheng Lab</organization>
      </author>
      <date day="31" month="October" year="2026"/>
      <abstract>
	 <t>   This document describes an infrastructure-assisted approach
   to the initial discovery of AI agents in managed enterprise,
   cloud, edge-computing, and communication-network
   environments. The approach treats infrastructure-provided
   resource state and requester context as possible inputs to
   the Minimum Viable Dataset (MVD) used by a discovery
   mechanism. These inputs can help keep minimum public
   discovery information current and can help determine the
   appropriate discovery scope or entry point without requiring
   the requester to understand deployment-specific network
   details. The document does not define registration, catalog
   search, semantic matchmaking, resource ranking, or selection,
   and does not define a new discovery wire protocol.

	 </t>
      </abstract>
   </front>
   <seriesInfo name="Internet-Draft" value="draft-dunbar-dawn-infra-assisted-discovery-03"/>
   
</reference>



    </references>

</references>


<?line 1104?>

<section numbered="false" anchor="acknowledgments"><name>Acknowledgments</name>

<t>The authors thank Adrian Farrel and Jim Mozley for early discussion in the
creation of this document, and their ongoing reviews and comments.</t>

<t>We also thank the following people for their DAWN mailing-list comments:
Tommy Jensen (concrete use cases), Mohamed Boucadair (discovery starting
points), Sumit Ahuja (capability discovery), Roman Danyliw (security and
privacy), Matthew Quick (cross-domain applicability), Pete Resnick (agent
identity considerations), and Mirja Kuehlewind (discovery steps).</t>

<t>Finally, we thank the following for their contribution to the use case practical
examples:</t>

<t><list style="symbols">
  <t>Revika Anand, Lancaster University</t>
  <t>Edward Revika, Lancaster University</t>
</list></t>

</section>


  </back>

<!-- ##markdown-source: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-->

</rfc>

