AGTP Agent Discovery and Name Service

1.1. The Discovery Layers

A deployed AGTP ecosystem contains agents registered across many organizations, governance zones, and trust tiers. An orchestrator agent that needs to delegate a task to a capable peer faces three distinct but related problems:¶

1. Population awareness: which agents are currently active and visible within my scope of operations?¶

2. Capability matching: among those visible agents, which can provide the capability I need?¶

3. Name resolution: given a human-readable name (such as concierge.acme.com), what is its Canonical Agent-ID?¶

These three problems are distinct and benefit from distinct mechanisms. Conflating them produces designs that are either too narrow (a single query interface that handles all three poorly) or too broad (a single registry that tries to be all things to all callers). This document specifies the application-layer interfaces for capability matching and name resolution, while deferring to [AGTP-PRESENCE] for population awareness.¶

1.2. Search, Discover, Resolve

Earlier revisions of this document and of [AGTP-PRESENCE] used "discovery" for all three problems. This revision adopts the distinction [RFC6763] draws for DNS-based service discovery and applies it to agents, because the three operations have different inputs, different outputs, and different trust properties:¶

Search:

The caller has a need and no identity. Input: capability criteria, an intent, trust and governance constraints. Output: a ranked list of candidate agents the caller had no prior knowledge of. Search is what the DISCOVER method does when invoked with intent or capability_domains. Its results are candidates to be evaluated, never agents to be trusted on the strength of the result.¶

Discover:

The caller has an identity and no current location. Input: a Canonical Agent-ID. Output: the agent's current attachment, the signed, short-lived record of where it can be reached, and its Identity Document ([AGTP-IDDOC]). The presence substrate of [AGTP-PRESENCE] provides discovery ambiently, and the DISCOVER method performs it when invoked against a known Agent-ID. Its result is bound to the identity by signature.¶

Resolve:

The caller has a name and no identity. Input: a human-readable name under a naming authority. Output: the Canonical Agent-ID the authority has bound to it. The Agent Name Service performs resolution. Its result is bound to the name by the authority's signature and is only as trustworthy as the authority.¶

The method is named DISCOVER for continuity with the registered AGTP method vocabulary and because its registry-resolved and presence-resolved modes are discovery in this sense; its intent-driven mode is search, and the text says so where it matters. An agent name and an agent address are aliases that resolve or discover to an Agent-ID; the Agent-ID is the identity, and nothing in this document treats a name or an address as one.¶

1.3. The Layered Architecture

The discovery architecture for AGTP is layered:¶

• AGTP-Presence [AGTP-PRESENCE] provides population awareness as a substrate-level property. Agents joining the AGTP network become ambiently aware of other agents within their visibility scope without requiring queries against a central directory.¶

• The DISCOVER method (specified in this document) provides the search interface. DISCOVER operates over the Presence substrate, filtering the ambient population by capability, trust posture, and governance constraints, and returns ranked candidates.¶

• Agent Name Service (ANS) (specified in this document) provides governed name-to-Agent-ID resolution, analogous to DNS for the web. ANS resolves human-readable names to Canonical Agent-IDs through federated name authorities. Resolution is distinct from search: a resolved name yields one identity bound by the authority's signature, where a search yields candidates.¶

• Anticipatory Discovery Services (ADS) (introduced as a forward-looking composition pattern in this document) provide application-layer services that observe agent operational signals and preload awareness of agents the observed agent is likely to need before explicit queries are issued.¶

Population awareness is the responsibility of [AGTP-PRESENCE] and is outside this document. This document specifies the application-layer query and naming interfaces that compose with that substrate.¶

1.4. Why Separate Search and Discovery From Naming

The internet has DNS for naming and presence systems (XMPP, Matrix) for population awareness as separate layers, because they answer different questions. DNS answers "what is the address for this name?" Presence systems answer "who is here right now?" These are different functions with different governance models, different update cadences, and different consumer use cases.¶

AGTP follows the same pattern. ANS is the naming layer, providing stable name-to-identifier mappings with the governance and federation properties that naming systems require. Presence is the population layer, providing ambient awareness with the convergence and visibility properties that population systems require. Conflating them, as some agent infrastructure proposals do, produces architectures that fit neither use case well.¶

1.5. Design Principles

Agent-native. Search, discovery, and naming results return Canonical Agent-IDs and Agent Identity Documents; no web page or proprietary record appears in a result. The result of a DISCOVER query is the same shape as the result of resolving a known agent URI.¶

Governed. ANS servers and DISCOVER endpoints are AGTP-aware infrastructure. They enforce trust tier requirements, behavioral trust score floors, and governance zone constraints before returning any result. ANS servers act as Scope-Enforcement Points for naming queries; DISCOVER endpoints act as Scope-Enforcement Points for capability queries.¶

Ranked. DISCOVER results are ranked by behavioral trust score, trust tier, and declared capability depth. The highest-quality agents matching the query appear first.¶

Brokered. DISCOVER endpoints MAY negotiate authority scope on behalf of the requesting agent, informing it of what scope is required to interact with each discovered agent before commitment.¶

Layered. This document leaves population awareness to [AGTP-PRESENCE]. The DISCOVER method and ANS compose with Presence and replicate none of its function.¶

3.1. Method Definition

DISCOVER is a floor method of [AGTP] and is registered in the IANA AGTP Method Registry. It is the protocol-level interface for agent search and for discovery of a known agent's attachment, operating over the AGTP-Presence substrate [AGTP-PRESENCE] for population awareness and against ANS servers for governed query brokering.¶

Purpose: Search for agents matching a capability description and governance constraints, or discover the current attachment of a known Agent-ID. Returns a ranked list of Agent Identity Documents drawn from the live presence layer (per [AGTP-PRESENCE]) within the requesting agent's visibility scope. The requesting agent MUST carry discovery:query in its Authority-Scope header to invoke DISCOVER.¶

Category: ACQUIRE. Idempotent: Yes.¶

3.2. Operational Modes

DISCOVER operates in three modes, distinguished by the endpoint it queries:¶

Direct Presence query. The requesting agent invokes DISCOVER against the local AGTP-Presence overlay coordinator. Results are drawn from agents currently visible in the requesting agent's visibility scope per the scoped overlay partitioning of [AGTP-PRESENCE]. This mode requires no ANS server.¶

ANS-brokered query. The requesting agent invokes DISCOVER against an ANS server. The ANS server combines its own indexed naming records with current Presence overlay state to return ranked results spanning both. ANS-brokered queries provide capability-aware ranking, scope negotiation, and cross-zone federation.¶

Cross-scope resolution. The requesting agent invokes DISCOVER with a capability or industry partition that resolves into a scope the agent has yet to join. The cross-scope resolution mechanism in [AGTP-PRESENCE] returns agent records from the target scope, which DISCOVER then ranks and returns to the requester.¶

The mode is determined by the request target. Implementations SHOULD prefer direct Presence queries for in-scope search and ANS-brokered queries for cross-zone or capability searches requiring governed brokering. A DISCOVER whose criteria name a single Agent-ID is a discovery in the sense of Section 1.2 in any mode; one that carries intent or capability_domains is a search.¶

3.3. Parameters

3.4. DISCOVER Request Example

AGTP/1.0 DISCOVER
Agent-ID: agtp://agtp.acme.tld/agents/orchestrator
Authority-Scope: discovery:query, agents:delegate
Request-Signature: <JWS per AGTP>
Session-ID: sess-discovery-01
Task-ID: task-disc-001
Content-Type: application/vnd.agtp+json

{
  "method": "DISCOVER",
  "task_id": "task-disc-001",
  "parameters": {
    "intent": "Audit smart contracts for security vulnerabilities",
    "capability_domains": ["methods", "tools"],
    "trust_tier_min": 1,
    "behavioral_trust_min": 0.85,
    "governance_zone": "zone:external-partner",
    "limit": 5,
    "scope_negotiate": true
  }
}

3.5. DISCOVER Request Example: Domain-Constrained Search

The following example illustrates a targeted DISCOVER query locating agents capable of auditing Solidity smart contracts within a specific governance zone and trust tier threshold. The requesting orchestrator carries discovery:query and agents:delegate scope, signaling that it intends to act on the results by delegating work.¶

AGTP/1.0 DISCOVER
Agent-ID: agtp://agtp.finco.tld/agents/orchestrator
Request-Signature: <JWS per AGTP>
Authority-Scope: discovery:query agents:delegate audit:*
Session-ID: sess-compliance-q2
Task-ID: task-disc-solidity-01
Content-Type: application/vnd.agtp+json

{
  "method": "DISCOVER",
  "task_id": "task-disc-solidity-01",
  "parameters": {
    "intent": "Audit Solidity smart contracts for reentrancy, overflow, and access control misconfiguration",
    "capability_domains": ["methods", "tools", "zones"],
    "trust_tier_min": 2,
    "behavioral_trust_min": 0.88,
    "governance_zone": "zone:finance",
    "limit": 3,
    "scope_negotiate": true
  }
}

The ANS server returns a ranked result set. The top result carries Trust Tier 1 with a behavioral trust score of 0.97, exposing the required_scope field indicating what the orchestrator must carry before a DELEGATE to this agent will be accepted:¶

{
  "status": 200,
  "task_id": "task-disc-solidity-01",
  "result": {
    "query_id": "qry-sc-audit-3c9f",
    "total_matches": 7,
    "returned": 3,
    "results": [
      {
        "rank": 1,
        "canonical_id": "4f7e1a2b9c3d...",
        "attachment": {
          "node": "9b21...a7d4",
          "binding": "quic",
          "endpoint": "agents.auditor.tld:4480",
          "mode": "full",
          "exp": 1793300000,
          "seq": 17
        },
        "identity_document_uri": "agtp://agtp.auditor.tld/agents/solidity-auditor",
        "available": true,
        "agent_label": "solidity-auditor",
        "org_domain": "auditor.tld",
        "trust_tier": 1,
        "behavioral_trust_score": 0.97,
        "supported_methods": ["QUERY", "ANALYZE", "VALIDATE", "REPORT"],
        "capability_match_score": 0.96,
        "governance_zone": "zone:finance",
        "required_scope": "audit:read code:analyze",
        "job_description": "Static and dynamic analysis of Solidity smart
                            contracts. Detects reentrancy, overflow, and
                            access control vulnerabilities."
      }
    ],
    "ans_signature": {
      "algorithm": "ES256",
      "key_id": "ans-key-finance-01",
      "value": "[base64-encoded-signature]"
    }
  }
}

The requesting agent verifies the ans_signature before trusting any result. It then issues a DESCRIBE to agtp://agtp.auditor.tld/agents/ solidity-auditor to confirm method support before committing to DELEGATE.¶

3.6. DISCOVER Response

The DISCOVER response body contains a ranked list of result entries, each carrying the agent's Canonical Agent-ID, its current attachment per [AGTP-PRESENCE] so that the result is reachable without a further resolution step, and optional scope negotiation fields:¶

{
  "status": 200,
  "task_id": "task-disc-001",
  "result": {
    "query_id": "qry-7f3a9c",
    "total_matches": 23,
    "returned": 5,
    "results": [
      {
        "rank": 1,
        "canonical_id": "3a9f2c1d8b7e4a6f...",
        "attachment": {
          "node": "7f3a...c2e1",
          "binding": "quic",
          "endpoint": "agents.auditor.tld:4480",
          "mode": "full",
          "exp": 1793300000,
          "seq": 42
        },
        "identity_document_uri": "agtp://agtp.auditor.tld/agents/contract-auditor",
        "available": true,
        "agent_label": "contract-auditor",
        "org_domain": "auditor.tld",
        "trust_tier": 1,
        "behavioral_trust_score": 0.97,
        "supported_methods": ["QUERY", "VALIDATE", "REPORT"],
        "capability_match_score": 0.94,
        "required_scope": "audit:read code:analyze",
        "job_description": "Static and dynamic analysis of Solidity smart contracts."
      }
    ],
    "ans_signature": {
      "algorithm": "ES256",
      "key_id": "ans-key-public-01",
      "value": "[base64-encoded-signature]"
    }
  }
}

The ans_signature covers the full result set including all manifests and the query_id. The requesting agent MUST verify the signature before trusting any discovery result. An unsigned or invalid DISCOVER response MUST be rejected.¶

3.7. Ranking Algorithm

ANS servers MUST rank results by a composite score computed as:¶

rank_score = (trust_tier_weight * normalized_trust_tier)
           + (behavioral_trust_weight * behavioral_trust_score)
           + (capability_match_weight * capability_match_score)

Default weights: trust_tier_weight = 0.3, behavioral_trust_weight = 0.4, capability_match_weight = 0.3. ANS servers MAY publish alternative weight configurations for domain-specific deployments.¶

The capability_match_score is computed by the ANS server as a normalized relevance score between the query's intent and capability_domains and the candidate agent's declared capabilities. The computation method is implementation-defined but MUST be deterministic for identical inputs.¶

4.1. ANS Architecture

The Agent Name Service provides governed resolution of human-readable names to Canonical Agent-IDs. ANS is the naming layer for AGTP, analogous to DNS for the web. ANS leaves to Presence the population awareness functionality provided by [AGTP-PRESENCE]; it provides the stable name-to-identifier mapping that complements ambient discovery in the sense of Section 1.2.¶

An ANS server is an AGTP endpoint that:¶

1. Maintains a registry of name-to-Agent-ID bindings for agents in its naming authority. The registry is structured for fast lookup on the name key, comparable to DNS zone file lookup.¶

2. Resolves DISCOVER queries that include name-based criteria by returning the bound Agent-ID and associated Agent Identity Document. ANS may consult the Presence overlay for current operational state of the resolved agent.¶

3. Enforces Trust Tier and behavioral trust score thresholds on all queries before returning results.¶

4. Signs all DISCOVER responses with the ANS's governance key.¶

5. Acts as a SEP for naming traffic: agents without discovery:query scope MUST be rejected with 455 Scope Violation.¶

ANS servers are themselves AGTP agents: they have canonical Agent-IDs, Agent Genesis records, and Agent Identity Documents. Their capabilities include discovery:query and discovery:register as Authority-Scope domains.¶

Multiple ANS servers MAY be deployed for different naming authorities, organizations, or trust tier populations. Cross-ANS federation is described in Section 5.¶

4.2. Relationship to Presence

ANS and AGTP-Presence are complementary layers serving different discovery use cases:¶

An agent's full discovery toolkit consists of all three: ambient awareness through Presence, governed name resolution through ANS, and capability-driven query through DISCOVER. These compose without duplication.¶

ANS servers MAY consult Presence overlay state when answering DISCOVER queries to ensure that resolved agents are currently reachable. An ANS-resolved name pointing to an Agent-ID that is no longer in any visible Presence overlay SHOULD be returned with an availability indicator, allowing the requesting agent to decide whether to attempt connection.¶

4.3. ANS Registration

An agent registers with an ANS server through a governed process tied to AGTP activation:¶

1. On completion of the AGTP ACTIVATE transaction, the governance platform automatically submits the agent's Agent Identity Document and DESCRIBE capability data to the designated ANS server(s) for the agent's governance zone.¶

2. The ANS server verifies the agent's lifecycle state is Active.¶

3. The ANS server indexes the agent's capabilities, trust tier, and behavioral trust score.¶

4. The ANS server updates its result index within 60 seconds.¶

Manual registration is unsupported. ANS registration is a consequence of AGTP activation, with no independent registration step. This ensures that only Active, registered agents appear in discovery results.¶

4.4. ANS Deregistration

When an agent's lifecycle state transitions to Suspended, Revoked, or Deprecated, the governance platform MUST notify the relevant ANS servers within 60 seconds. The ANS server MUST remove the agent from its result index before the next DISCOVER request is processed.¶

ANS servers MUST treat deregistration as urgent: a Revoked agent that continues to appear in discovery results is a governance failure. ANS servers MUST log deregistration events.¶

4.5. Index Freshness

ANS servers MUST refresh capability data for indexed agents at a configurable interval (recommended: 24 hours). Refresh is triggered by issuing DESCRIBE requests to each indexed agent's canonical URI. If an agent fails to respond to a DESCRIBE request after three consecutive attempts, the ANS server MUST remove it from the index and notify the governance platform.¶

5.1. The Federation Problem

An agent in one naming authority may need to resolve names registered in a different authority. Organization-scoped ANS servers lack visibility into other organizations' naming records.¶

Naming federation in ANS follows the DNS root and TLD hierarchy. Cross-organizational name resolution proceeds through established federation patterns at the naming authority layer. Population federation across organizations is handled separately by the cross-scope resolution mechanism in [AGTP-PRESENCE].¶

5.2. Federation Protocol

AGTP supports a federated discovery model in which ANS servers can query peer ANS servers on behalf of requesting agents. A federated DISCOVER query:¶

1. The requesting agent sends a DISCOVER request to its local ANS server.¶

2. If the local ANS server's index holds insufficient results (fewer than limit results above the requested thresholds), it MAY forward the query to federated peer ANS servers it trusts.¶

3. Federated queries MUST carry the original requesting agent's Agent-ID and scope requirements. The forwarding ANS server MUST NOT expand the scope or lower the trust requirements in the forwarded query.¶

4. Peer ANS servers apply their own governance policies to the forwarded query and return signed result sets.¶

5. The local ANS server merges, re-ranks, and re-signs the combined result set before returning it to the requesting agent.¶

6. The merged result includes a federation_path field listing the ANS servers that contributed results.¶

5.3. Trust in Federation

Federated ANS results MUST be treated with the same trust level as the federated ANS server's own Trust Tier claim. An ANS server MUST declare the trust tier of its indexed agents accurately; misrepresenting agent trust tiers in federated results is a governance violation.¶

6.1. Capability-Based Routing

ANS servers MAY support dynamic routing: when a requesting agent's preferred target agent is unavailable (lifecycle state Suspended, absent from responding, or rate-limited), the ANS server MAY return an equivalent agent from its index as a routing alternative.¶

Dynamic routing responses MUST indicate: - routing_reason: the reason the primary agent was withheld - equivalent_confidence: a score (0.0-1.0) indicating how closely the alternative matches the primary agent's capabilities¶

The requesting agent retains the right to reject the alternative.¶

6.2. Agent Availability Signals

ANS servers SHOULD monitor indexed agents' availability by periodically checking the /status sub-resource defined in [AGTP-IDDOC]. Agents with lifecycle_state: Suspended or active_session_count at capacity SHOULD be marked as unavailable in routing responses.¶

7.1. The Anticipatory Pattern

Baseline discovery in AGTP combines ambient awareness within Presence overlays, governed name resolution through ANS, and capability-driven query through DISCOVER. An agent's effective awareness is bounded by the scopes it has joined and the queries it explicitly issues.¶

Anticipatory Discovery Services expand this awareness proactively. An ADS observes an agent's operational signals (methods invoked, capabilities accessed, recent peers, principal context, time-of-day patterns) and predicts which categories of agents the observed agent is likely to need next. ADS then preloads awareness of relevant agents through proactive Presence overlay joining or rendezvous lookups, before the observed agent has issued an explicit DISCOVER query.¶

The pattern is analogous to anticipatory service in hospitality: recognizing that a guest walking toward the pool will need towels and providing them before the request is articulated. The signal precedes the explicit ask; the response is preloaded based on the observed pattern.¶

7.2. Architectural Position

ADS is an application-layer service, above the substrate. It composes with the layers specified elsewhere in the AGTP draft family:¶

• AGTP base provides the wire-level identity and methods¶

• [AGTP-TRUST] provides trust posture for filtering predictions¶

• [AGTP-PRESENCE] provides the population substrate that ADS expands awareness within¶

• This document provides the DISCOVER and ANS mechanisms that ADS proactively invokes on behalf of observed agents¶

ADS operates as a service that agents subscribe to or organizations host. It uses AGTP primitives (DISCOVER queries, ANS resolutions, Presence overlay joining, attribution records) but is outside the substrate itself.¶

7.3. Composable ADS Providers

This document explicitly accommodates multiple deployment models for ADS:¶

Self-hosted ADS. Organizations operate their own ADS for their agents. The model is trained on the organization's own data. Operational signals never leave the org. Anticipatory benefit is bounded by the org's own scale and pattern diversity.¶

Trust-tier-scoped ADS. ADS services operate per trust tier, observing patterns within a tier and serving anticipatory predictions to participating agents. Cross-organizational learning improves predictions; privacy is managed through aggregated or differentially private signal exchange.¶

Specialized provider ADS. Just as trust providers can specialize (as described in [AGTP-TRUST]), ADS providers may specialize by capability domain, industry vertical, or trust tier. A finance ADS for trading agents, a consumer-services ADS for retail agents, a healthcare ADS for clinical agents. Agents subscribe to one or more ADS providers appropriate to their domain.¶

Capability-derived ADS. ADS scoped per capability dimension (per the partition model in [AGTP-PRESENCE]). Capability-specific prediction models operate within each capability scope, with cross-scope coordination through standard federation patterns.¶

7.4. Trust and Privacy Considerations

ADS observes operational patterns that may include sensitive information about agent activity, principals served, capabilities accessed, and interaction patterns. Several mitigations are acknowledged in this outline; full specification is deferred:¶

• ADS subscription MUST be opt-in. Agents that never subscribe to any ADS provider operate with baseline Presence and on-demand ANS/DISCOVER without anticipatory preloading.¶

• ADS providers MUST scope their predictions within the visibility constraints of the observed agent. ADS expands discovery within existing access; it grants no access the agent would otherwise lack.¶

• Local-only ADS deployments preserve privacy by keeping operational signals within the organizational boundary.¶

• ADS providers that aggregate signals across organizations SHOULD apply differential privacy or aggregate-only observation patterns.¶

7.5. Forward-Looking Composition

ADS is positioned in this document as an architectural concept worth specifying. The agent population is growing; the operational sophistication of agent discovery is going to grow with it. ADS represents a natural composition pattern where application-layer services consume AGTP primitives to provide value beyond what the substrate or the basic query interfaces deliver on their own.¶

Future revisions or companion documents will specify:¶

• The signal vocabulary that ADS providers ingest¶

• The prediction interface between ADS and observed agents¶

• The preloading protocol for proactive Presence overlay joining¶

• Privacy semantics for cross-organizational signal aggregation¶

• Feedback mechanisms for prediction quality assessment¶

This document establishes the architectural slot for ADS within the AGTP discovery layer, naming the pattern and positioning it as a composable application-layer service alongside the credit-rating trust providers described in [AGTP-TRUST].¶

8.1. Discovery Result Injection

Threat: A malicious ANS server returns forged Agent Identity Documents pointing to attacker-controlled agents.¶

Mitigation: All DISCOVER responses MUST be signed by the ANS server's governance key. The requesting agent MUST verify the ans_signature field before trusting any result. The ANS server's governance key MUST be resolvable via the ANS server's own Agent Identity Document, creating a verifiable trust chain.¶

8.2. Discovery Enumeration

Threat: A malicious agent uses repeated DISCOVER queries to enumerate all agents in a governance zone, gaining knowledge of the organization's agent architecture.¶

Mitigation: ANS servers MUST enforce rate limiting per requesting Agent-ID. ANS servers MAY require discovery:query scope to include agents from restricted governance zones. ANS servers SHOULD log high-frequency DISCOVER queries as anomaly signals.¶

8.3. Behavioral Trust Score Manipulation

Threat: An agent artificially inflates its behavioral trust score to appear higher in discovery results.¶

Mitigation: Behavioral trust scores are computed by the governance platform's pre-packaging verification pipeline and embedded in the agent's .agent or .nomo package at issuance time. The score is part of the signed manifest and cannot be modified without invalidating the package integrity hash. ANS servers MUST use the trust score from the verified Agent Identity Document; agent-asserted fields are ignored.¶

8.4. Scope Negotiation Abuse

Threat: An ANS server inflates the required_scope field in discovery results, causing requesting agents to request broader scope than necessary.¶

Mitigation: Requesting agents MUST NOT blindly request the scope declared in discovery results. The required_scope field is informational; agents MUST evaluate the scope against their own authorization and request only what is needed for the specific task. Governance platforms SHOULD flag scope requests that significantly exceed the scope of prior tasks in the same session.¶

9.1. DISCOVER Method Registration

This document requests registration of the DISCOVER method in the IANA AGTP Method Registry established by [AGTP]:¶

9.2. New Authority-Scope Domains

This document uses the following Authority-Scope domains defined in [AGTP] Appendix A:¶

No new domains are requested; these are from the existing reserved set.¶

10.1. Normative References

[AGTP]

Hood, C., "Agent Transfer Protocol (AGTP)", Work in Progress, Internet-Draft, draft-hood-independent-agtp-10, 2026, <https://datatracker.ietf.org/doc/html/draft-hood-independent-agtp-10>.

[RFC2119]

Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, DOI 10.17487/RFC2119, March 1997, <https://www.rfc-editor.org/rfc/rfc2119>.

[RFC8174]

Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC 2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174, May 2017, <https://www.rfc-editor.org/rfc/rfc8174>.

10.2. Informative References

[AGTP-IDDOC]

Hood, C., "AGTP Agent Identity Document", Work in Progress, Internet-Draft, draft-hood-agtp-identity-document-00, 2026, <https://datatracker.ietf.org/doc/html/draft-hood-agtp-identity-document-00>.

[AGTP-PRESENCE]

Hood, C., "AGTP Presence: Ambient Discovery and Visibility for Agents", Work in Progress, Internet-Draft, draft-hood-agtp-presence-01, 2026, <https://datatracker.ietf.org/doc/html/draft-hood-agtp-presence-01>.

[AGTP-TRUST]

Hood, C., "AGTP Trust and Verification Specification", Work in Progress, Internet-Draft, draft-hood-agtp-trust-03, 2026, <https://datatracker.ietf.org/doc/html/draft-hood-agtp-trust-03>.

[DAWN-INFRA]

Dunbar, L., "Infrastructure-Assisted Discovery of AI Agents", Work in Progress, Internet-Draft, draft-dunbar-dawn-infra-assisted-discovery, 2026, <https://datatracker.ietf.org/doc/html/draft-dunbar-dawn-infra-assisted-discovery>.

[RFC6763]

Cheshire, S. and M. Krochmal, "DNS-Based Service Discovery", RFC 6763, DOI 10.17487/RFC6763, February 2013, <https://www.rfc-editor.org/rfc/rfc6763>.

B.1. Infrastructure-Assisted Discovery

[DAWN-INFRA] describes managed enterprise, edge, and network deployments in which discovery is fed by two infrastructure inputs: a Resource Publication Hook, through which an orchestration or hosting system supplies the discovery mechanism with the agent instances currently deployed and their endpoints, and an Attachment Context Hook, through which the network supplies an abstract representation of the requester's current attachment (site, VPN, tenant, slice, edge region). The motivating failure is a discovery system that keeps returning an instance that has been withdrawn or is unreachable from where the requester now is. AGTP meets the same need with one publish event and one verified identity in place of two feeds, and the mapping is stated here for readers coming from that work.¶

The Resource Publication Hook is ACTIVATE. A successful ACTIVATE is the publish event of [AGTP]: it triggers registration with the ANS of the agent's zone (Section 4) and the first ANNOUNCE into the presence substrate ([AGTP-PRESENCE]), and DEACTIVATE, REVOKE, and DEPRECATE are the withdrawal events. The dynamic half of what the hook would carry, the current endpoint, is the attachment record of [AGTP-PRESENCE]: signed by the agent, sequenced, and short-lived, so that a withdrawn or moved instance expires out of discovery on its own and a stale attachment yields nothing an attacker can use. An orchestrator that instantiates, moves, scales, or withdraws instances does so through the lifecycle methods, and discovery follows without a side channel.¶

The Attachment Context Hook divides into two inputs that AGTP already binds to the requester. Administrative context (tenant, VPN, organization, governance zone) is a property of the requester's verified identity: the governance_zone and org_domain of the Identity Document the requester's Agent-ID resolves to, under the issuer's signature. That is why the DISCOVER governance-zone rule of [AGTP] needs no network hook: the server reads the requester's zone from the document it has already verified. Location context (which site or edge region the requester is attached to) is the requester's own presence: the overlays it has joined and the attachment record it has itself announced per [AGTP-PRESENCE], whose region partition dimension carries exactly the site and edge granularity the use case needs. In both cases the context arrives signed and bound to the requester, with no middlebox inferring it, which is the integrity, origin, and freshness protection [DAWN-INFRA] asks for in its security considerations, and the underlying network detail (UPF, DNN, slice, serving gateway) stays with the network, since the abstract context is all the requester's identity and attachment expose.¶

The use case's own boundary, that discovery returns the applicable entities and leaves selection to the requester, is the search line of Section 1.2: DISCOVER returns ranked candidates, each with its current attachment, and the requester chooses.¶

On the word itself: [DAWN-INFRA] uses "attachment" for the requester's network attachment, this family uses it for the discovered agent's. They are the same network term, where a node attaches, applied to the two parties of a discovery. Both parties have an attachment; AGTP publishes the target's as the attachment record and uses the requester's as search context.¶

D.1. Substantive Changes

The following substantive changes were made in v01:¶

1. Layered architecture framing. The introduction now establishes the three distinct discovery problems (population awareness, capability matching, name resolution) and assigns each to its appropriate layer ([AGTP-PRESENCE], the DISCOVER method, and ANS respectively). The document no longer presents ANS as the primary discovery mechanism; ANS is now positioned as the naming layer that composes with Presence.¶

2. DISCOVER over Presence substrate. The DISCOVER method is now specified to operate over the AGTP-Presence substrate as its primary mode, with ANS-brokered queries and cross-scope resolution as additional operational modes. The method's wire format is unchanged.¶

3. ANS reframed as name resolution. The Agent Name Service section now positions ANS as a governed name-to-Agent-ID resolution layer analogous to DNS, complementing the population awareness provided by AGTP-Presence. A new "Relationship to Presence" subsection makes the layered composition explicit.¶

4. Anticipatory Discovery Services introduced. A new section (Section 7) introduces ADS as a forward-looking composition pattern where application-layer services preload agent awareness based on observed operational signals. The architectural concept is named and positioned; full specification is deferred to future work.¶

5. Informative references added. AGTP-PRESENCE and AGTP-TRUST are added to the informative references. Cross-references throughout the document point to the appropriate layer for population awareness, trust posture consumption, and credit-rating-analogous trust provider composition.¶

D.2. Wire Format Compatibility

The DISCOVER method wire format is unchanged. Implementations conforming to v00 of this document continue to interoperate with v01. The architectural reframing affects how the document describes the relationships between layers; the protocol behavior that v00 implementations have shipped is the same.¶