<?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 2.6.10) -->


<!DOCTYPE rfc  [
  <!ENTITY nbsp    "&#160;">
  <!ENTITY zwsp   "&#8203;">
  <!ENTITY nbhy   "&#8209;">
  <!ENTITY wj     "&#8288;">

]>


<rfc ipr="trust200902" docName="draft-stafordtituss-agentic-mandate-evidence-00" category="info" submissionType="IETF" tocInclude="true" sortRefs="true" symRefs="true">
  <front>
    <title abbrev="Agent Continuity Evaluation">Continuity Evaluation of Agent Delegation Records</title>

    <author fullname="Staford Titus Selvaraj">
      <organization>Independent</organization>
      <address>
        <email>stafordtituss@gmail.com</email>
      </address>
    </author>

    <date year="2026" month="November" day="17"/>

    <area>Security</area>
    <workgroup>AUDIT BOF</workgroup>
    <keyword>agents</keyword> <keyword>delegation</keyword> <keyword>audit</keyword> <keyword>authorization</keyword> <keyword>continuity</keyword>

    <abstract>


<?line 44?>

<t>The AUDIT architecture defines records that capture the user's intent, delegation, authorization state, and the actions that agents take across trust boundaries. Records alone don't answer the question an auditor, an operator, or a relying party asks next: did the executed effect stay within the authority the user delegated?</t>

<t>This document defines a deterministic, three-valued evaluation over such records. The outcomes are preserved, violated, and unresolved, and every non-preserved outcome names the invariant that was broken. The document also defines the claim model that the evaluation needs, the roles permitted to sign each record, a mapping onto the AUDIT record types, and a set of interoperable test vectors. It is derived from the Agentic Mandate Evidence Protocol (AMEP).</t>



    </abstract>



  </front>

  <middle>


<?line 50?>

<section anchor="introduction"><name>Introduction</name>

<t>AI agents act through chains of delegation: a user to an agent, an agent to sub-agents, and agents to tools, adapters, and services. Each hop can widen what is done relative to what was asked. Common examples:</t>

<t><list style="symbols">
  <t>an approval for one command is reused for another;</t>
  <t>a sub-agent receives broader scope than its parent held;</t>
  <t>untrusted content steers a mutation;</t>
  <t>an adapter maps a tool call to an effect that differs from the one declared;</t>
  <t>a decision made after the fact, from an audit log, is presented as if it had prevented the action.</t>
</list></t>

<t><xref target="I-D.kuehlewind-audit-architecture"/> defines Interaction, Action, Delegation, and Authorization Transition records, and the propagation of audit context, so that these chains can be reconstructed.</t>

<t>This document is complementary. Given a set of such records, it specifies:</t>

<t><list style="numbers" type="1">
  <t>a <strong>claim model</strong> that makes delegated authority machine-checkable (actions, resources, deny lists, data classes, an effect ceiling, validity, a delegation budget, and an optional risk budget);</t>
  <t><strong>signer roles</strong>, so that a record counts as evidence only when it is signed by a party entitled to make it;</t>
  <t><strong>invariants</strong> that a chain of records must satisfy (I1 to I11);</t>
  <t>a deterministic <strong>evaluation procedure</strong> that returns preserved, violated, or unresolved, together with the deciding invariant;</t>
  <t><strong>test vectors</strong>, so that independent verifiers can demonstrate that they agree.</t>
</list></t>

<t>The evaluation can run before an effect, when an enforcement point decides on the predicted effect, or after the fact, when an auditor evaluates recorded effects. It never treats missing evidence as success, and it never treats a post-execution decision as a block.</t>

<section anchor="requirements-language"><name>Requirements Language</name>

<t>The key words "<bcp14>MUST</bcp14>", "<bcp14>MUST NOT</bcp14>", "<bcp14>REQUIRED</bcp14>", "<bcp14>SHALL</bcp14>", "<bcp14>SHALL
NOT</bcp14>", "<bcp14>SHOULD</bcp14>", "<bcp14>SHOULD NOT</bcp14>", "<bcp14>RECOMMENDED</bcp14>", "<bcp14>NOT RECOMMENDED</bcp14>",
"<bcp14>MAY</bcp14>", and "<bcp14>OPTIONAL</bcp14>" in this document are to be interpreted as
described in BCP 14 <xref target="RFC2119"/> <xref target="RFC8174"/> when, and only when, they
appear in all capitals, as shown here.</t>

<?line -18?>

</section>
<section anchor="terminology"><name>Terminology</name>

<t>This document uses the roles of <xref target="I-D.kuehlewind-audit-architecture"/>: User, Agent, Tool/Service, Auditing Service, Audit Store, Transparency Log, and Auditor. It adds:</t>

<dl>
  <dt>Mandate:</dt>
  <dd>
    <t>a signed claim set issued for a principal, stating what an agent may do on the principal's behalf.</t>
  </dd>
  <dt>Intent:</dt>
  <dd>
    <t>an optional claim set derived from a single request (for example, a prompt), narrower than the mandate.</t>
  </dd>
  <dt>Invocation:</dt>
  <dd>
    <t>a declared call to a tool or service, made under a mandate (possibly delegated).</t>
  </dd>
  <dt>Effect:</dt>
  <dd>
    <t>what was actually executed at the boundary where the action took effect.</t>
  </dd>
  <dt>Observer:</dt>
  <dd>
    <t>the party that produced the effect record.</t>
  </dd>
  <dt>Verifier:</dt>
  <dd>
    <t>an entity that runs the evaluation in <xref target="evaluation"/>.</t>
  </dd>
</dl>

</section>
</section>
<section anchor="mapping"><name>Relationship to the AUDIT Architecture</name>

<texttable>
      <ttcol align='left'>This document</ttcol>
      <ttcol align='left'>AUDIT record type</ttcol>
      <ttcol align='left'>What is evaluated</ttcol>
      <c>Mandate, Intent</c>
      <c>Interaction Record (prompt, signed grant)</c>
      <c>claim set C (<xref target="claims"/>)</c>
      <c>Delegation</c>
      <c>Delegation Record</c>
      <c>attenuation, I1</c>
      <c>Approval</c>
      <c>Interaction Record (approval, HITL escalation)</c>
      <c>binding to the exact effect, I8</c>
      <c>Invocation and interpretation</c>
      <c>Action Record (declared)</c>
      <c>interpretation provenance (I3), influence (I4)</c>
      <c>Effect</c>
      <c>Action Record (at the effect boundary)</c>
      <c>I2, I5, I9, I10, I11</c>
      <c>Grant, revocation, status</c>
      <c>Authorization Transition Record</c>
      <c>liveness, I6</c>
      <c>Continuity decision</c>
      <c>(none)</c>
      <c>the output of this document, with its phase</c>
</texttable>

<t>Mandates and delegations commonly originate in OAuth 2.0 Token Exchange chains <xref target="RFC8693"/>. Records <bcp14>MAY</bcp14> be carried as COSE_Sign1 objects <xref target="RFC9052"/>, and <bcp14>MAY</bcp14> be registered with a transparency service <xref target="I-D.ietf-scitt-architecture"/>, which makes selective omission of records detectable.</t>

<t>This document doesn't define new transport or storage. It requires only that records carry the fields listed in <xref target="fields"/>, and that records can be linked using the AUDIT audit context: trace, parent, actor, and on-behalf-of.</t>

</section>
<section anchor="claims"><name>Claim Model</name>

<t>A claim set is C = (A, R, A⁻, R⁻, D, E, V, P, K, B), where:</t>

<t><list style="symbols">
  <t>A and R are sets of canonical action and resource patterns that are permitted;</t>
  <t>A⁻ and R⁻ are sets of action and resource patterns that are denied even when A or R would permit them;</t>
  <t>D is a set of (data class, recipient class) pairs;</t>
  <t>E is the effect ceiling, an element of the totally ordered set <spanx style="verb">read &lt; write_local &lt; write_shared &lt; external_send &lt; destructive &lt; financial</spanx>;</t>
  <t>V is the validity interval;</t>
  <t>P is the purpose;</t>
  <t>K is the delegation budget (remaining depth);</t>
  <t>B is an <bcp14>OPTIONAL</bcp14> risk budget in points.</t>
</list></t>

<t>C1 ⊑ C2 (C1 is equal to or narrower than C2) holds if and only if: every pattern in A1 and R1 is subsumed by some pattern in A2 or R2 respectively; every pattern in A2⁻ and R2⁻ is subsumed by some pattern in A1⁻ or R1⁻ respectively (denies only grow); D1 ⊆ D2; E1 ≤ E2; V1 ⊆ V2; P1 = P2 or P2 is unrestricted; the depth rule holds (if K2 is present, K2 &gt; 0 and K1 &lt; K2); and B1 ≤ B2 when B2 is present.</t>

<t>The meet C1 ⊓ C2 is taken component-wise, with denies unioned so that no hop and no intent can lift a deny.</t>

<t>Resource identifiers <bcp14>MUST</bcp14> be canonical. File-system paths <bcp14>MUST</bcp14> be absolute and normalized, with the home directory expanded and ".." collapsed. URLs <bcp14>MUST</bcp14> carry their resolved host class. SaaS objects <bcp14>MUST</bcp14> be identified as <spanx style="verb">provider:type/id</spanx>. A verifier <bcp14>MUST NOT</bcp14> rely on user-relative forms.</t>

<t>An effect is x = (a, r, d, e, t). x ⊨ C if and only if a matches A and not A⁻, r matches R and not R⁻, e ≤ E, every released (data class, recipient class) pair is in D, and t ∈ V.</t>

</section>
<section anchor="roles"><name>Signer Roles</name>

<t>A valid signature shows only that a key signed a record. Each key in the verifier's key set carries roles, and a record counts as signed only when its key holds a role permitted for the record's kind:</t>

<texttable>
      <ttcol align='left'>Record</ttcol>
      <ttcol align='left'>Permitted signer roles</ttcol>
      <c>Mandate, revocation, revocation status</c>
      <c>issuer</c>
      <c>Delegation, intent</c>
      <c>issuer, host</c>
      <c>Interpretation, invocation, decision</c>
      <c>host</c>
      <c>Effect</c>
      <c>observer</c>
      <c>Approval</c>
      <c>approver</c>
      <c>Content finding</c>
      <c>host, observer</c>
</texttable>

<t>Without roles, a compromised host key could mint its own mandate or approve its own action.</t>

</section>
<section anchor="invariants"><name>Invariants</name>

<texttable>
      <ttcol align='left'>ID</ttcol>
      <ttcol align='left'>Invariant</ttcol>
      <ttcol align='left'>When broken</ttcol>
      <c>I1</c>
      <c>Attenuation: child ⊑ parent at every delegation edge</c>
      <c>violated</c>
      <c>I2</c>
      <c>Every effect matches the declared (or mediated) effect, satisfies the meet of the chain (and of the intent), and stays within risk budgets unless a bound approval covers it</c>
      <c>violated</c>
      <c>I3</c>
      <c>The invocation was interpreted by an approved, version-pinned mapping</c>
      <c>unresolved</c>
      <c>I4</c>
      <c>Content withheld by a quarantine did not reach a later step; a mutation influenced by content that is not signed and trusted was confirmed by the principal</c>
      <c>violated (executed) or unresolved</c>
      <c>I5</c>
      <c>Data classes released to a recipient are permitted</c>
      <c>violated</c>
      <c>I6</c>
      <c>No ancestor was revoked, per signed revocation or status evidence, at or before the invocation</c>
      <c>violated</c>
      <c>I7</c>
      <c>All required records are present, well-formed, signed by a permitted role, and fresh where required</c>
      <c>unresolved</c>
      <c>I8</c>
      <c>An approval matches the executed effect (without its time), is within its validity window, unconsumed, and used once</c>
      <c>violated</c>
      <c>I9</c>
      <c>No agent effect targets guardrail configuration, keys, instruction files, or the audit store</c>
      <c>violated</c>
      <c>I10</c>
      <c>An effect at or above <spanx style="verb">write_shared</spanx> names its actor and was observed by a party other than that actor</c>
      <c>unresolved</c>
      <c>I11</c>
      <c>Every recorded effect links to an authorized invocation, and none exists for an invocation a pre-execution decision denied</c>
      <c>violated</c>
</texttable>

</section>
<section anchor="evaluation"><name>Evaluation Procedure</name>

<t>For each invocation, in recorded order, a verifier <bcp14>MUST</bcp14> apply the following checks in order and return the first outcome that applies. "Verified" means signed by a key holding a permitted role (<xref target="roles"/>).</t>

<figure><artwork><![CDATA[
ID   Outcome     Condition
I4   violated    quarantined content in the influence set,
                 not confirmed by the principal
I7   unresolved  no root mandate
I7   unresolved  cited intent missing, or a needed record
                 not verified
I7   unresolved  lineage names an invocation that is not earlier
I3   unresolved  no approved interpretation, or a pin mismatch
I1   violated    a delegation edge where not (child ⊑ parent)
I6   violated    verified revocation or status shows an
                 ancestor revoked
I7   unresolved  unverified revocation on the chain, or a
                 revocable record without a fresh verified status
I9   violated    guardrail target
I4   violated    untrusted influence on a mutation, unconfirmed
                 (unresolved instead if no effect exists)
I7   unresolved  no effect record
     For every effect record of the invocation:
I7   unresolved    record not verified
I10  unresolved    e >= write_shared and the actor is absent,
                   the effect is self-observed, or assurance L0
I2   violated      executed != declared (and != the mediated
                   effect)
I9   violated      executed resource is a guardrail
I2   violated      x does not satisfy the meet of the chain and
                   intent (I5 when the failure is a release)
I5   violated      data classes carried in through lineage reach
                   a recipient class the claims do not permit
I7   unresolved  approval missing or not verified
I8   violated    approval unbound, outside its window,
                 consumed, or reused
I7   violated    recorded budget spend != recomputed cost
I2   violated    risk budget exceeded without a bound approval
-    preserved   otherwise
]]></artwork></figure>

<t>After all invocations:</t>

<figure><artwork><![CDATA[
ID   Outcome     Condition
I11  violated    pre-execution deny/hold decision, and an effect
                 exists (enforcement contradicted)
-    preserved   pre-execution deny/hold decision, no effect,
                 enforcement fail-closed or applied = confirmed
I11  violated    effect with no invocation
]]></artwork></figure>

<t>Lineage: an effect may record the data classes it read (accessed) and the recipient class of what it sent; an invocation may name the earlier invocations its input came from (derived_from). The data classes an invocation carries are those its own effects read plus those carried by the invocations it derives from, transitively. This detects sensitive data leaving in a later step even when that step declares no release.</t>

<t>A verifier evaluating a stream of packets <bcp14>MAY</bcp14> carry approval use and risk-budget spending from one packet to the next, so that single use and budgets hold across the stream.</t>

<t>Decisions carry a phase: pre_execution, post_execution, or simulation. Only pre-execution decisions can confirm or contradict a block. A post-execution decision is detection and <bcp14>MUST NOT</bcp14> be presented as having prevented the action.</t>

<t>When B is present, the cost of x is base(e) × m(d) × rev(x). The base table is read 0, write_local 1, write_shared 3, external_send 5, destructive 10, financial 20. m(d) is the largest data-class multiplier among the released classes (1, 2, or 5). rev(x) is 1 if the effect is a read, or reversible and not an external send, and 3 otherwise. The cost is charged to every node in the chain. The tables are registries (<xref target="iana"/>).</t>

</section>
<section anchor="fields"><name>Required Fields</name>

<t>The evaluation needs the following fields from each AUDIT record. Field names are placeholders until the AUDIT data model is defined.</t>

<t><list style="symbols">
  <t>Mandate, Intent, and Delegation: id, parent, issuer, claims (C), signature.</t>
  <t>Invocation: id, authority reference, interpretation reference (adapter and version), declared effect, actor, influence references, approval reference, time.</t>
  <t>Effect: id, invocation reference, executed effect x, observer, assurance level (L0 self-reported to L3 provider-confirmed), signature.</t>
  <t>Approval: id, effect digest (SHA-256 over the JCS <xref target="RFC8785"/> form of x without its time), presence (webauthn, chat_user, host_ui, or none), validity window, consumed flag, signature.</t>
  <t>Revocation and revocation status: target, time (or as-of time and revocation time), signature.</t>
  <t>Continuity decision: invocation reference, mode, phase, outcome, enforcement context (enforcement point, fail mode, what was returned to the host, whether an effect record confirms it), signature.</t>
</list></t>

<t>Records are canonicalized with JCS <xref target="RFC8785"/> and signed with Ed25519 <xref target="RFC8032"/>. Times are numbers of seconds since the epoch or RFC 3339 <xref target="RFC3339"/> strings. A CDDL <xref target="RFC8610"/> definition and JSON Schemas are published in <xref target="AMEP"/>.</t>

</section>
<section anchor="test-vectors"><name>Test Vectors</name>

<t><xref target="AMEP"/> publishes 95 vectors: 25 positive and 70 must-reject. The must-reject vectors cover all eleven invariants, signer roles, revocation status, decision phase, deny lists, data lineage, state across packets, risk-budget accounting, and a deny that an executed effect contradicts. Each vector is a packet of signed records, with the expected outcome and invariant. Two independently written implementations (Python, and JavaScript run under Node.js and in a browser) agree on all 95.</t>

<t>A conforming verifier <bcp14>MUST</bcp14> return the expected outcome and invariant for every vector.</t>

</section>
<section anchor="implementation-status"><name>Implementation Status</name>

<t><strong>Note to the RFC Editor:</strong> please remove this section before publication, per <xref target="RFC7942"/>.</t>

<t><list style="symbols">
  <t><strong>AMEP reference verifiers.</strong> Two independent implementations: Python, and JavaScript (run as a Node.js command-line tool and as an offline browser page using WebCrypto). Both evaluate the procedure in <xref target="evaluation"/> and agree on all 95 published vectors. License: Apache 2.0. Location: https://github.com/stafordtituss/amep. Maturity: prototype.</t>
  <t><strong>Natsar control plane</strong> (agent-authority enforcement for coding-agent hosts and MCP). It emits decision records before tool execution from host hooks. Maturity: pre-release.</t>
</list></t>

<t>Implementation experience motivated several parts of this document: canonical resource identifiers (absolute-path forms bypassed relative-prefix rules); recording the enforcement context and phase (hosts differ in whether they support "ask" and whether hook failures block); and treating an effect that contradicts a deny as evidence of bypass.</t>

</section>
<section anchor="security-considerations"><name>Security Considerations</name>

<t><list style="symbols">
  <t><strong>Adversarial models:</strong> the guarantees <bcp14>MUST</bcp14> hold even if every model in the chain is adversarial. Semantic analysis <bcp14>MAY</bcp14> raise a decision level, but <bcp14>MUST NOT</bcp14> mint authority or lower a decision.</t>
  <t><strong>Self-reporting:</strong> records produced by the actor alone are insufficient for high-impact effects (I10).</t>
  <t><strong>Key compromise:</strong> signer roles (<xref target="roles"/>) limit what one stolen key can forge.</t>
  <t><strong>Evidence omission:</strong> a missing record, status or signature yields unresolved. Omission of whole invocations is detected only against an independent effect log (I11).</t>
  <t><strong>Canonicalization:</strong> non-canonical resource forms enable bypasses. Canonicalization is therefore normative.</t>
  <t><strong>Approval replay and time-of-check/time-of-use:</strong> approvals bind the exact effect and are single use (I8).</t>
  <t><strong>Fail-open enforcement:</strong> an enforcement point that errors <bcp14>MUST</bcp14> return a deny decision, not a transport error. Hosts commonly treat transport errors as non-blocking, and some treat an unsupported "ask" as a hook failure and run the action. A verifier <bcp14>SHOULD</bcp14> treat an effect that contradicts a pre-execution deny as evidence of bypass.</t>
  <t><strong>Guardrail tampering:</strong> agent writes to hook configuration, keys, instruction files, or the audit store are violations (I9).</t>
</list></t>

</section>
<section anchor="privacy-considerations"><name>Privacy Considerations</name>

<t>Effect records can contain personal data. Verifiers need only canonical actions, resource identifiers, data-class labels, and digests. Payloads <bcp14>SHOULD</bcp14> be detached and hashed, following the AUDIT selective-disclosure work.</t>

</section>
<section anchor="iana"><name>IANA Considerations</name>

<t>This document proposes registries for effect classes, data classes, recipient classes, signer roles, and the risk-cost tables, with the registration policy Specification Required. The registries are to be defined in a later revision.</t>

</section>


  </middle>

  <back>


<references title='References' anchor="sec-combined-references">

    <references title='Normative References' anchor="sec-normative-references">



<reference anchor="RFC8785">
  <front>
    <title>JSON Canonicalization Scheme (JCS)</title>
    <author fullname="A. Rundgren" initials="A." surname="Rundgren"/>
    <author fullname="B. Jordan" initials="B." surname="Jordan"/>
    <author fullname="S. Erdtman" initials="S." surname="Erdtman"/>
    <date month="June" year="2020"/>
    <abstract>
      <t>Cryptographic operations like hashing and signing need the data to be expressed in an invariant format so that the operations are reliably repeatable. One way to address this is to create a canonical representation of the data. Canonicalization also permits data to be exchanged in its original form on the "wire" while cryptographic operations performed on the canonicalized counterpart of the data in the producer and consumer endpoints generate consistent results.</t>
      <t>This document describes the JSON Canonicalization Scheme (JCS). This specification defines how to create a canonical representation of JSON data by building on the strict serialization methods for JSON primitives defined by ECMAScript, constraining JSON data to the Internet JSON (I-JSON) subset, and by using deterministic property sorting.</t>
    </abstract>
  </front>
  <seriesInfo name="RFC" value="8785"/>
  <seriesInfo name="DOI" value="10.17487/RFC8785"/>
</reference>
<reference anchor="RFC8032">
  <front>
    <title>Edwards-Curve Digital Signature Algorithm (EdDSA)</title>
    <author fullname="S. Josefsson" initials="S." surname="Josefsson"/>
    <author fullname="I. Liusvaara" initials="I." surname="Liusvaara"/>
    <date month="January" year="2017"/>
    <abstract>
      <t>This document describes elliptic curve signature scheme Edwards-curve Digital Signature Algorithm (EdDSA). The algorithm is instantiated with recommended parameters for the edwards25519 and edwards448 curves. An example implementation and test vectors are provided.</t>
    </abstract>
  </front>
  <seriesInfo name="RFC" value="8032"/>
  <seriesInfo name="DOI" value="10.17487/RFC8032"/>
</reference>
<reference anchor="RFC3339">
  <front>
    <title>Date and Time on the Internet: Timestamps</title>
    <author fullname="G. Klyne" initials="G." surname="Klyne"/>
    <author fullname="C. Newman" initials="C." surname="Newman"/>
    <date month="July" year="2002"/>
    <abstract>
      <t>This document defines a date and time format for use in Internet protocols that is a profile of the ISO 8601 standard for representation of dates and times using the Gregorian calendar.</t>
    </abstract>
  </front>
  <seriesInfo name="RFC" value="3339"/>
  <seriesInfo name="DOI" value="10.17487/RFC3339"/>
</reference>
<reference anchor="RFC2119">
  <front>
    <title>Key words for use in RFCs to Indicate Requirement Levels</title>
    <author fullname="S. Bradner" initials="S." surname="Bradner"/>
    <date month="March" year="1997"/>
    <abstract>
      <t>In many standards track documents several words are used to signify the requirements in the specification. These words are often capitalized. This document defines these words as they should be interpreted in IETF documents. This document specifies an Internet Best Current Practices for the Internet Community, and requests discussion and suggestions for improvements.</t>
    </abstract>
  </front>
  <seriesInfo name="BCP" value="14"/>
  <seriesInfo name="RFC" value="2119"/>
  <seriesInfo name="DOI" value="10.17487/RFC2119"/>
</reference>
<reference anchor="RFC8174">
  <front>
    <title>Ambiguity of Uppercase vs Lowercase in RFC 2119 Key Words</title>
    <author fullname="B. Leiba" initials="B." surname="Leiba"/>
    <date month="May" year="2017"/>
    <abstract>
      <t>RFC 2119 specifies common key words that may be used in protocol specifications. This document aims to reduce the ambiguity by clarifying that only UPPERCASE usage of the key words have the defined special meanings.</t>
    </abstract>
  </front>
  <seriesInfo name="BCP" value="14"/>
  <seriesInfo name="RFC" value="8174"/>
  <seriesInfo name="DOI" value="10.17487/RFC8174"/>
</reference>



    </references>

    <references title='Informative References' anchor="sec-informative-references">



<reference anchor="RFC7942">
  <front>
    <title>Improving Awareness of Running Code: The Implementation Status Section</title>
    <author fullname="Y. Sheffer" initials="Y." surname="Sheffer"/>
    <author fullname="A. Farrel" initials="A." surname="Farrel"/>
    <date month="July" year="2016"/>
    <abstract>
      <t>This document describes a simple process that allows authors of Internet-Drafts to record the status of known implementations by including an Implementation Status section. This will allow reviewers and working groups to assign due consideration to documents that have the benefit of running code, which may serve as evidence of valuable experimentation and feedback that have made the implemented protocols more mature.</t>
      <t>This process is not mandatory. Authors of Internet-Drafts are encouraged to consider using the process for their documents, and working groups are invited to think about applying the process to all of their protocol specifications. This document obsoletes RFC 6982, advancing it to a Best Current Practice.</t>
    </abstract>
  </front>
  <seriesInfo name="BCP" value="205"/>
  <seriesInfo name="RFC" value="7942"/>
  <seriesInfo name="DOI" value="10.17487/RFC7942"/>
</reference>
<reference anchor="RFC8610">
  <front>
    <title>Concise Data Definition Language (CDDL): A Notational Convention to Express Concise Binary Object Representation (CBOR) and JSON Data Structures</title>
    <author fullname="H. Birkholz" initials="H." surname="Birkholz"/>
    <author fullname="C. Vigano" initials="C." surname="Vigano"/>
    <author fullname="C. Bormann" initials="C." surname="Bormann"/>
    <date month="June" year="2019"/>
    <abstract>
      <t>This document proposes a notational convention to express Concise Binary Object Representation (CBOR) data structures (RFC 7049). Its main goal is to provide an easy and unambiguous way to express structures for protocol messages and data formats that use CBOR or JSON.</t>
    </abstract>
  </front>
  <seriesInfo name="RFC" value="8610"/>
  <seriesInfo name="DOI" value="10.17487/RFC8610"/>
</reference>
<reference anchor="RFC8693">
  <front>
    <title>OAuth 2.0 Token Exchange</title>
    <author fullname="M. Jones" initials="M." surname="Jones"/>
    <author fullname="A. Nadalin" initials="A." surname="Nadalin"/>
    <author fullname="B. Campbell" initials="B." role="editor" surname="Campbell"/>
    <author fullname="J. Bradley" initials="J." surname="Bradley"/>
    <author fullname="C. Mortimore" initials="C." surname="Mortimore"/>
    <date month="January" year="2020"/>
    <abstract>
      <t>This specification defines a protocol for an HTTP- and JSON-based Security Token Service (STS) by defining how to request and obtain security tokens from OAuth 2.0 authorization servers, including security tokens employing impersonation and delegation.</t>
    </abstract>
  </front>
  <seriesInfo name="RFC" value="8693"/>
  <seriesInfo name="DOI" value="10.17487/RFC8693"/>
</reference>
<reference anchor="RFC9052">
  <front>
    <title>CBOR Object Signing and Encryption (COSE): Structures and Process</title>
    <author fullname="J. Schaad" initials="J." surname="Schaad"/>
    <date month="August" year="2022"/>
    <abstract>
      <t>Concise Binary Object Representation (CBOR) is a data format designed for small code size and small message size. There is a need to be able to define basic security services for this data format. This document defines the CBOR Object Signing and Encryption (COSE) protocol. This specification describes how to create and process signatures, message authentication codes, and encryption using CBOR for serialization. This specification additionally describes how to represent cryptographic keys using CBOR.</t>
      <t>This document, along with RFC 9053, obsoletes RFC 8152.</t>
    </abstract>
  </front>
  <seriesInfo name="STD" value="96"/>
  <seriesInfo name="RFC" value="9052"/>
  <seriesInfo name="DOI" value="10.17487/RFC9052"/>
</reference>

<reference anchor="I-D.kuehlewind-audit-architecture">
   <front>
      <title>An Architecture for Auditing Agent Delegation and Interactions</title>
      <author fullname="Mirja Kühlewind" initials="M." surname="Kühlewind">
         <organization>Ericsson</organization>
      </author>
      <author fullname="Henk Birkholz" initials="H." surname="Birkholz">
         <organization>Fraunhofer SIT</organization>
      </author>
      <date day="7" month="September" year="2026"/>
      <abstract>
	 <t>   This document describes an architecture for auditing of agent-driven
   interactions on the Internet.  Autonomous and semi-autonomous
   software agents, including those based on artificial intelligence,
   increasingly act on behalf of users, organizations, and services.
   Existing auditing mechanisms often capture isolated system events but
   do not consistently represent delegation relationships, user intent,
   or evolving authorization.  In agent-driven systems, auditability
   requires linking intent, delegation, authorization, and execution.
   The proposed architecture enables this through distributed audit
   record generation, propagation of audit context, optional
   attestation, and additional logging for transparency.

	 </t>
      </abstract>
   </front>
   <seriesInfo name="Internet-Draft" value="draft-kuehlewind-audit-architecture-01"/>
   
</reference>

<reference anchor="I-D.ietf-scitt-architecture">
   <front>
      <title>An Architecture for Trustworthy and Transparent Digital Supply Chains</title>
      <author fullname="Henk Birkholz" initials="H." surname="Birkholz">
         <organization>Fraunhofer SIT</organization>
      </author>
      <author fullname="Antoine Delignat-Lavaud" initials="A." surname="Delignat-Lavaud">
         <organization>Microsoft Research</organization>
      </author>
      <author fullname="Cedric Fournet" initials="C." surname="Fournet">
         <organization>Microsoft Research</organization>
      </author>
      <author fullname="Yogesh Deshpande" initials="Y." surname="Deshpande">
         <organization>ARM</organization>
      </author>
      <author fullname="Steve Lasker" initials="S." surname="Lasker">
         </author>
      <date day="10" month="October" year="2025"/>
      <abstract>
	 <t>   Traceability in supply chains is a growing security concern.  While
   verifiable data structures have addressed specific issues, such as
   equivocation over digital certificates, they lack a universal
   architecture for all supply chains.  This document defines such an
   architecture for single-issuer signed statement transparency.  It
   ensures extensibility, interoperability between different
   transparency services, and compliance with various auditing
   procedures and regulatory requirements.

	 </t>
      </abstract>
   </front>
   <seriesInfo name="Internet-Draft" value="draft-ietf-scitt-architecture-22"/>
   
</reference>

<reference anchor="AMEP" target="https://github.com/stafordtituss/amep">
  <front>
    <title>Agentic Mandate Evidence Protocol (AMEP) v0.2</title>
    <author initials="S. T." surname="Selvaraj" fullname="Staford Titus Selvaraj">
      <organization></organization>
    </author>
    <date year="2026"/>
  </front>
</reference>


    </references>

</references>


<?line 293?>

<section numbered="false" anchor="acknowledgments"><name>Acknowledgments</name>

<t>This document is derived from the Agentic Mandate Evidence Protocol (AMEP), designed and written by the author.</t>

</section>


  </back>

<!-- ##markdown-source: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-->

</rfc>

