Individual Submission D. King
Internet-Draft Lancaster University
Intended status: Informational K. Yao
Expires: 14 March 2027 China Mobile
K. Adler
Indeed
R. Ramdhany
BBC
10 September 2026
Use Cases and Applicability for Discovery of Agents With Names
draft-kay-dawn-use-cases-01
Abstract
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.
This document does not define a discovery protocol, a registration
procedure, a selection algorithm, or an agent-to-agent communication
protocol.
About This Document
This note is to be removed before publishing as an RFC.
Status information for this document may be found at
https://datatracker.ietf.org/doc/draft-kay-dawn-use-cases/.
Discussion of this document takes place on the Individual Submission
Individual mailing list (mailto:dawn@ietf.org), which is archived at
https://mailarchive.ietf.org/arch/browse/dawn/. Subscribe at
https://www.ietf.org/mailman/listinfo/dawn/.
Status of This Memo
This Internet-Draft is submitted in full conformance with the
provisions of BCP 78 and BCP 79.
Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF). Note that other groups may also distribute
working documents as Internet-Drafts. The list of current Internet-
Drafts is at https://datatracker.ietf.org/drafts/current/.
King, et al. Expires 14 March 2027 [Page 1]
Internet-Draft DAWN Use Cases September 2026
Internet-Drafts are draft documents valid for a maximum of six months
and may be updated, replaced, or obsoleted by other documents at any
time. It is inappropriate to use Internet-Drafts as reference
material or to cite them other than as "work in progress."
This Internet-Draft will expire on 14 March 2027.
Copyright Notice
Copyright (c) 2026 IETF Trust and the persons identified as the
document authors. All rights reserved.
This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents (https://trustee.ietf.org/
license-info) in effect on the date of publication of this document.
Please review these documents carefully, as they describe your rights
and restrictions with respect to this document. Code Components
extracted from this document must include Revised BSD License text as
described in Section 4.e of the Trust Legal Provisions and are
provided without warranty as described in the Revised BSD License.
Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3
2. Limitations of this Document . . . . . . . . . . . . . . . . 4
3. Terminology . . . . . . . . . . . . . . . . . . . . . . . . . 5
4. Applicability . . . . . . . . . . . . . . . . . . . . . . . . 6
5. Discovery Characteristics . . . . . . . . . . . . . . . . . . 7
6. Discovery Pattern . . . . . . . . . . . . . . . . . . . . . . 8
7. Categories of Discovery . . . . . . . . . . . . . . . . . . . 9
7.1. Capability-Oriented Discovery . . . . . . . . . . . . . . 9
7.1.1. Assumptions . . . . . . . . . . . . . . . . . . . . . 9
7.1.2. Discovery Impacts . . . . . . . . . . . . . . . . . . 9
7.1.3. Examples . . . . . . . . . . . . . . . . . . . . . . 9
7.2. Resource-Oriented Discovery . . . . . . . . . . . . . . . 9
7.2.1. Assumptions . . . . . . . . . . . . . . . . . . . . . 10
7.2.2. Discovery Impacts . . . . . . . . . . . . . . . . . . 10
7.2.3. Examples . . . . . . . . . . . . . . . . . . . . . . 10
7.3. Administrative Scope Extensions . . . . . . . . . . . . . 11
7.3.1. Assumptions . . . . . . . . . . . . . . . . . . . . . 11
7.3.2. Discovery Impacts . . . . . . . . . . . . . . . . . . 11
7.3.3. Examples . . . . . . . . . . . . . . . . . . . . . . 11
7.4. Operational Discovery . . . . . . . . . . . . . . . . . . 12
7.4.1. Assumptions . . . . . . . . . . . . . . . . . . . . . 12
7.4.2. Discovery Impacts . . . . . . . . . . . . . . . . . . 12
7.4.3. Examples . . . . . . . . . . . . . . . . . . . . . . 12
8. Classes of Use Case . . . . . . . . . . . . . . . . . . . . . 13
8.1. AI Agent . . . . . . . . . . . . . . . . . . . . . . . . 13
King, et al. Expires 14 March 2027 [Page 2]
Internet-Draft DAWN Use Cases September 2026
8.2. Software Service . . . . . . . . . . . . . . . . . . . . 13
8.3. Compute Workload . . . . . . . . . . . . . . . . . . . . 13
8.4. Network Function . . . . . . . . . . . . . . . . . . . . 13
8.5. Application Endpoint . . . . . . . . . . . . . . . . . . 13
9. Security Considerations . . . . . . . . . . . . . . . . . . . 13
10. Privacy Considerations . . . . . . . . . . . . . . . . . . . 14
11. Operational Considerations . . . . . . . . . . . . . . . . . 14
12. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 15
13. References . . . . . . . . . . . . . . . . . . . . . . . . . 15
13.1. Normative References . . . . . . . . . . . . . . . . . . 15
13.2. Informative References . . . . . . . . . . . . . . . . . 15
Appendix A. Cross-Organisation Appointment Coordination . . . . 16
A.1. Actors and Assumptions . . . . . . . . . . . . . . . . . 16
A.2. Initial Discovery at a Known Organisation . . . . . . . . 17
A.3. Supporting Resource Discovery and Restaurant
Reservation . . . . . . . . . . . . . . . . . . . . . . . 17
A.4. Reconnection and Rediscovery . . . . . . . . . . . . . . 19
A.5. Discovery Information Needed in This Scenario . . . . . . 20
A.6. Security, Privacy, and Operational Considerations . . . . 21
A.7. Links to the DAWN Requirements . . . . . . . . . . . . . 21
Appendix B. Provisioning Edge Compute for Personalised Live
Media . . . . . . . . . . . . . . . . . . . . . . . . . . 22
B.1. Actors and Assumptions . . . . . . . . . . . . . . . . . 23
B.2. Discovery and Provisioning . . . . . . . . . . . . . . . 23
B.3. Changes During the Broadcast . . . . . . . . . . . . . . 24
B.4. Security and Privacy . . . . . . . . . . . . . . . . . . 24
B.5. Links to the DAWN Requirements . . . . . . . . . . . . . 24
Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . . . 25
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 25
1. Introduction
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.
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.
King, et al. Expires 14 March 2027 [Page 3]
Internet-Draft DAWN Use Cases September 2026
The DAWN problem statement
[I-D.akhavain-moussa-dawn-problem-statement] and the DAWN
requirements document [I-D.king-dawn-requirements] provide background
for this work. These use cases inform the Discovery Architecture,
which will define the requirements and minimum discovery information.
This document defines the following categories of entity discovery:
1. Capability-Oriented Discovery, where an entity needs to discover
another entity that can provide a function or capability.
2. Resource-Oriented Discovery, where discovery identifies resources
used in AI systems.
3. Administrative Scope Extensions, where discovery crosses
organisational, delegation, or tenancy boundaries within the
applicable trust relationships.
4. Operational Discovery, where discovery supports operation, audit,
troubleshooting, compliance, or automation.
The first two categories are base cases. The others describe common
extensions or deployments of those base cases.
Other Internet-Drafts describe agentic AI discovery use cases and
communication protocol requirements, including
[I-D.mozley-aidiscovery], [I-D.agentic-ai-usecases-requirements], and
[I-D.scrm-aiproto-usecases].
2. Limitations of this Document
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.
The following are in scope:
* discovery of a specific named AI resource;
* discovery of candidate AI resources by capability or other
discovery properties within the applicable deployment;
* discovery of tasks as resources in an AI system;
* discovery initiated by an agent, workload, service, application,
or human operator;
King, et al. Expires 14 March 2027 [Page 4]
Internet-Draft DAWN Use Cases September 2026
* discovery of supporting resources used by AI agents and
applications;
* exchange of the minimum discovery information, directly or by
indirection, before selection, invocation, or communication can
take place.
The following are out of scope:
* registration of entities for discovery;
* authentication or attestation of registrations;
* design, definition, or governance of naming systems;
* identity management of AI agents, tools, and skills;
* trust management and trust evaluation beyond protecting content
exchanged between discovery participants;
* selection among candidate entities returned by discovery;
* exchange of capability information beyond the minimum discovery
information defined by the Architecture work;
* capability negotiation after discovery;
* all application communication beyond the discovery process;
* task orchestration;
* standalone certificate or key lookup services; and
* AI resource indexing across the wider Internet, general search,
ranking, or marketplace discovery.
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.
3. Terminology
Terminology for DAWN is defined in [I-D.farrel-dawn-terminology].
Attention is drawn to the following specific terms defined in
[I-D.farrel-dawn-terminology] that are key to this document:
King, et al. Expires 14 March 2027 [Page 5]
Internet-Draft DAWN Use Cases September 2026
* discovering entity
* discovered entity
* discoverable object
* discovery information
* minimum discoverable information
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.
The appendix also uses the following implementation term:
Agent harness 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. Opensource examples of an agent
harness include: OpenClaw and Hermes.
4. Applicability
The categories in Section 7 apply in three settings:
King, et al. Expires 14 March 2027 [Page 6]
Internet-Draft DAWN Use Cases September 2026
+===============+=======================+===========================+
| Deployment | Illustrative | Applicability condition |
| | discovery need | |
+===============+=======================+===========================+
| Local network | An assistant finds a | Discovery visibility is |
| | nearby inference | local; using the service |
| | service advertised on | remains subject to |
| | its local network. | application permissions. |
+---------------+-----------------------+---------------------------+
| Within an | An enterprise | Publication and access |
| organisation | assistant finds an | follow the |
| | internal data source | organisation's existing |
| | or tool. | administrative and trust |
| | | arrangements. |
+---------------+-----------------------+---------------------------+
| Between | An assistant finds a | The organisations have a |
| cooperating | partner's calendar- | trust relationship; |
| organisations | coordination agent. | discovery finds |
| | | resources within that |
| | | relationship. |
+---------------+-----------------------+---------------------------+
Table 1
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.
DNS and mDNS are possible discovery mechanisms; others may also be
suitable. Protocol work should reuse existing IETF mechanisms where
possible.
5. Discovery Characteristics
The use cases share a common question: what must a client discover
before it can attempt interaction with an entity?
* Discovery may be initiated by autonomous software or by a human
operator.
* The discovered target may be a specific named entity or a set of
entities determined by properties or classification.
* 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.
King, et al. Expires 14 March 2027 [Page 7]
Internet-Draft DAWN Use Cases September 2026
* The minimum discovery information may change over time. Freshness
and caching therefore matter even when detailed runtime properties
are obtained later through application interaction.
* Discovery may need to account for entities that are dynamic,
mobile, or available only in a particular context.
* 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.
* 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.
6. Discovery Pattern
The use cases in this document follow a common pattern.
1. A discovering entity has a task, intent, policy requirement, or
operational need.
2. The discovering entity needs to find an entity, or class of
entities, that can satisfy that need.
3. The discovering entity forms a discovery request using
information such as a name, organisation, entity type,
capability, location, jurisdiction, communication protocol, or
policy constraint.
4. The discovery mechanism returns information about one or more
candidate entities.
5. The discovering entity uses that information to decide whether
selection, authorisation, capability exchange, or communication
should be attempted.
The last step is outside the scope of discovery. However, discovery
has to return enough information for this step to be possible.
The Architecture determines which query properties belong in minimum
discovery information. Other constraints are evaluated by the
application.
King, et al. Expires 14 March 2027 [Page 8]
Internet-Draft DAWN Use Cases September 2026
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.
7. Categories of Discovery
Each category includes assumptions, discovery impacts, and examples
within the settings in Section 4.
7.1. Capability-Oriented Discovery
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.
7.1.1. Assumptions
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.
7.1.2. Discovery Impacts
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.
7.1.3. Examples
A scheduling assistant needs to find a calendar-coordination agent at
a partner organisation and learn how to contact it. The appendix
develops this example in Appendix A.
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.
7.2. Resource-Oriented Discovery
A client needs to discover resources supporting an AI system, such as
data sources, knowledge bases, models, inference services, or compute
services.
King, et al. Expires 14 March 2027 [Page 9]
Internet-Draft DAWN Use Cases September 2026
7.2.1. Assumptions
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.
It also assumes that some discovery information may be sensitive.
Data classification, model provenance, jurisdiction, permitted use,
and operational capacity may need visibility controls.
7.2.2. Discovery Impacts
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.
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.
7.2.3. Examples
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.
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.
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.
King, et al. Expires 14 March 2027 [Page 10]
Internet-Draft DAWN Use Cases September 2026
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.
7.3. Administrative Scope Extensions
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.
7.3.1. Assumptions
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.
7.3.2. Discovery Impacts
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.
Publication scope helps the client interpret a result. Discovery
must also avoid exposing sensitive tenant or organisational structure
to unauthorised parties.
7.3.3. Examples
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.
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.
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.
King, et al. Expires 14 March 2027 [Page 11]
Internet-Draft DAWN Use Cases September 2026
7.4. Operational Discovery
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.
7.4.1. Assumptions
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.
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.
7.4.2. Discovery Impacts
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.
Management and diagnostics for the discovery system itself may also
be needed so that operators can understand discovery behaviour and
failures.
Brokers, directory services, and operational tools may themselves be
discovery targets when they support an AI system.
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.
7.4.3. Examples
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.
King, et al. Expires 14 March 2027 [Page 12]
Internet-Draft DAWN Use Cases September 2026
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.
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.
8. Classes of Use Case
The taxonomy in [I-D.akhavain-moussa-dawn-problem-statement] provides
background for classifying AI resources and their supporting
entities.
8.1. AI Agent
TBD
8.2. Software Service
TBD
8.3. Compute Workload
TBD
8.4. Network Function
TBD
8.5. Application Endpoint
TBD
9. Security Considerations
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.
King, et al. Expires 14 March 2027 [Page 13]
Internet-Draft DAWN Use Cases September 2026
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.
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.
Security of discovery metadata is distinct from trust in the
discovered entity. Authentication, authorisation, attestation, and
policy checks for later interaction are outside discovery.
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.
10. Privacy Considerations
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.
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.
Privacy-sensitive information can include proprietary capabilities,
deployment location, capacity, runtime state, model or dataset
metadata, requester identity, search history, and query intent.
11. Operational Considerations
Enterprise, cloud, and edge deployments have different needs for
publication, caching, freshness, authorisation, observability, and
operational control.
King, et al. Expires 14 March 2027 [Page 14]
Internet-Draft DAWN Use Cases September 2026
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.
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.
Across administrative domains, operational considerations include
publication authority, caching, freshness, visibility controls,
logging, abuse handling, and failure behaviour.
12. IANA Considerations
This document has no IANA actions.
13. References
13.1. Normative References
[I-D.farrel-dawn-terminology]
Farrel, A., Yao, K., Schott, R., and N. Williams,
"Terminology for the Discovery of Agents, Workloads, and
Named Entities (DAWN)", Work in Progress, Internet-Draft,
draft-farrel-dawn-terminology-04, 26 July 2026,
<https://datatracker.ietf.org/doc/html/draft-farrel-dawn-
terminology-04>.
13.2. Informative References
[I-D.agentic-ai-usecases-requirements]
Reddy.K, T., Sarker, Z., and K. Yao, "Agentic AI Use Cases
and Requirements", Work in Progress, Internet-Draft,
draft-agentic-ai-usecases-requirements-02, 25 August 2026,
<https://datatracker.ietf.org/doc/html/draft-agentic-ai-
usecases-requirements-02>.
King, et al. Expires 14 March 2027 [Page 15]
Internet-Draft DAWN Use Cases September 2026
[I-D.akhavain-moussa-dawn-problem-statement]
Akhavain, A., Moussa, H., and D. King, "Problem Statement
for the Discovery of Agents, Workloads, and Named Entities
(DAWN)", Work in Progress, Internet-Draft, draft-akhavain-
moussa-dawn-problem-statement-05, 19 July 2026,
<https://datatracker.ietf.org/doc/html/draft-akhavain-
moussa-dawn-problem-statement-05>.
[I-D.king-dawn-requirements]
King, D. and A. Farrel, "Requirements for the Discovery of
Agents, Workloads, and Named Entities (DAWN)", Work in
Progress, Internet-Draft, draft-king-dawn-requirements-01,
28 April 2026, <https://datatracker.ietf.org/doc/html/
draft-king-dawn-requirements-01>.
[I-D.mozley-aidiscovery]
Mozley, J., Williams, N., Sarikaya, B., and R. Schott, "AI
Agent Discovery (AID) Problem Statement", Work in
Progress, Internet-Draft, draft-mozley-aidiscovery-01, 16
April 2026, <https://datatracker.ietf.org/doc/html/draft-
mozley-aidiscovery-01>.
[I-D.scrm-aiproto-usecases]
Schott, R., Maisonneuve, J., Contreras, L. M., and J. Ros-
Giralt, "Taxonomy for Agentic AI Use Cases", Work in
Progress, Internet-Draft, draft-scrm-aiproto-usecases-05,
4 July 2026, <https://datatracker.ietf.org/doc/html/draft-
scrm-aiproto-usecases-05>.
Appendix A. Cross-Organisation Appointment Coordination
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.
The example combines capability and resource discovery across an
organisational boundary, then shows how Hermes can reuse what it has
learned.
A.1. Actors and Assumptions
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.
King, et al. Expires 14 March 2027 [Page 16]
Internet-Draft DAWN Use Cases September 2026
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.
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.
Alice is assumed to supply enough context to distinguish the intended
Bob.
A.2. Initial Discovery at a Known Organisation
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.
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.
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.
A.3. Supporting Resource Discovery and Restaurant Reservation
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.
With a suitable time identified, Hermes proceeds as follows:
King, et al. Expires 14 March 2027 [Page 17]
Internet-Draft DAWN Use Cases September 2026
1. Discover the restaurant-booking service through the cooperating
provider's discovery entry point. The result identifies the
booking capability and how to contact it.
2. 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.
3. Present a suitable option to Alice and ask her to confirm the
restaurant, time, and any booking conditions.
4. On confirmation, request the reservation through the service and
retain its booking reference. Report whether the reservation
succeeded.
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.
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.
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--| | |
| | | |
King, et al. Expires 14 March 2027 [Page 18]
Internet-Draft DAWN Use Cases September 2026
A.4. Reconnection and Rediscovery
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.
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.
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.
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.
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.
King, et al. Expires 14 March 2027 [Page 19]
Internet-Draft DAWN Use Cases September 2026
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-----| | |
| | | |
A.5. Discovery Information Needed in This Scenario
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:
* the entity's name, type, and a service or capability identifier;
* reachability information and supported communication methods; and
* references used to obtain that minimum information through
indirection.
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.
King, et al. Expires 14 March 2027 [Page 20]
Internet-Draft DAWN Use Cases September 2026
A.6. Security, Privacy, and Operational Considerations
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.
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.
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.
A.7. Links to the DAWN Requirements
The scenario illustrates several requirements in
[I-D.king-dawn-requirements].
King, et al. Expires 14 March 2027 [Page 21]
Internet-Draft DAWN Use Cases September 2026
+===============================+===================================+
| Part of the scenario | Related requirements |
+===============================+===================================+
| Finding a calendar or booking | REQ-DISC-2: discovery by |
| capability, then reconnecting | function or specific |
| to a known entity. | instance; REQ-CLASS-2: |
| | classification by capability. |
+-------------------------------+-----------------------------------+
| Starting at each | REQ-PROTO-4: predictable |
| organisation's discovery | entry points; REQ-ARCH-4: |
| entry point. | independent publication. |
+-------------------------------+-----------------------------------+
| Obtaining the endpoint and | REQ-PROP-2: communication |
| protocol needed to contact | protocols and transport |
| the service. | parameters, directly or by |
| | reference. |
+-------------------------------+-----------------------------------+
| Keeping cached discovery | REQ-PROP-4 and REQ-PROP-11: |
| information separate from | property change rates and |
| live calendar and table | their implications for |
| availability. | caching and refresh. |
+-------------------------------+-----------------------------------+
| Protecting discovery | REQ-SEC-1: authenticity and |
| responses and restricting who | integrity; REQ-SEC-4: |
| can see them. | visibility controls. |
+-------------------------------+-----------------------------------+
| Recording the discovery | REQ-SEC-7: auditability of |
| source and decisions to | discovery operations. |
| refresh or repeat a query. | |
+-------------------------------+-----------------------------------+
| Using separate application | REQ-DISC-4: discovery's place |
| exchanges to select a | in the interaction workflow. |
| restaurant, confirm with | |
| Alice, and reserve a table. | |
+-------------------------------+-----------------------------------+
Table 2
Appendix B. Provisioning Edge Compute for Personalised Live Media
A broadcaster offers a personalised live programme [object-based
media delivery]. Viewers may chooses 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.
King, et al. Expires 14 March 2027 [Page 22]
Internet-Draft DAWN Use Cases September 2026
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.
B.1. Actors and Assumptions
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 provides
audience forecasts and information about compute and network
conditions.
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.
Agentic Resource Discovery (ARD)
(https://agenticresourcediscovery.org/) is possible interface to a
provider's catalogue in this scenario. It provide 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 endpoints 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.
B.2. Discovery and Provisioning
1. 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.
2. 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.
3. 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.
King, et al. Expires 14 March 2027 [Page 23]
Internet-Draft DAWN Use Cases September 2026
4. Subject to the operator's policy and authorisation, the
allocation agent requests provisioning through the site
controllers. It reports result, or explains why the available
resources cannot meet the request.
The diagram summarises discovery and the later application exchanges.
The agents contact each service separately.
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-------------------|
Discovery provides the information needed to contact an entity.
Comparing sites, reserving compute, steering traffic, and delivering
media are application activities outside DAWN.
B.3. Changes During the Broadcast
Audience demand or site availbility may change. The agents can reuse
valid discovery information and query current conditions through the
data services. Changed or expired discovery records may requires a
refresh or a new query. Moving workloads or adding capacity remains
an application decision.
B.4. Security and Privacy
Discovery information is integrity-protected, including across
provider boundaries, and its origin and freshness are checked.
Finding a controller does not grants permission to provision
resources. Viewer details and detailed capacity data are restricted
to authorised application exchanges.
B.5. Links to the DAWN Requirements
The example reuses requirements in [I-D.king-dawn-requirements]:
* REQ-DISC-2 and REQ-CLASS-2: finding entities by function or
capability.
King, et al. Expires 14 March 2027 [Page 24]
Internet-Draft DAWN Use Cases September 2026
* REQ-PROP-2: obtaining communication details, directly or by
reference.
* REQ-PROP-4 and REQ-PROP-11: distinguishing cached discovery
information from frequently changing resource data.
* REQ-SEC-1 and REQ-SEC-4: protecting discovery information and
controlling its visibility.
* REQ-???
Acknowledgments
The authors thank Adrian Farrel and Jim Mozley for early discussion
in the creation of this document, and their ongoing reviews and
comments.
We also thank the following peopl 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), Lori Jakab (local network
discovery), Matthew Quick (cross-domain applicability), Pete Resnick
(agent identity considerations), and Mirja Kuehlewind (discovery
steps).
Finally, we thank the following for their contribution to the use
case practical examples:
* Revika Anand, Lancaster University
* Edward Revika, Lancaster University
Authors' Addresses
Daniel King
Lancaster University
Email: d.king@lancaster.ac.uk
Kehan Yao
China Mobile
Email: yaokehan@chinamobile.com
Ken Adler
Indeed
Email: kadler@indeed.com
King, et al. Expires 14 March 2027 [Page 25]
Internet-Draft DAWN Use Cases September 2026
Rajiv Ramdhany
BBC
Email: rajiv.ramdhany@bbc.co.uk
King, et al. Expires 14 March 2027 [Page 26]