<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE rfc [
  <!ENTITY nbsp "&#160;">
]>
<rfc xmlns:xi="http://www.w3.org/2001/XInclude"
     category="info"
     docName="draft-agrawal-agentproto-presented-output-00"
     ipr="trust200902"
     submissionType="IETF"
     tocInclude="true"
     sortRefs="true"
     symRefs="true"
     xml:lang="en"
     version="3">

  <front>
    <title abbrev="Presented Output Use Case">Use Case and Requirements for Reporting Output Presented to a User</title>
    <seriesInfo name="Internet-Draft" value="draft-agrawal-agentproto-presented-output-00"/>

    <author fullname="Chirag Agrawal" initials="C." surname="Agrawal">
      <address>
        <email>chirag.agrawal93@gmail.com</email>
      </address>
    </author>

    <date year="2026" month="November" day="15"/>

    <workgroup>Agent Communication Protocols</workgroup>

    <keyword>agent</keyword>
    <keyword>dialog</keyword>
    <keyword>voice</keyword>
    <keyword>interruption</keyword>
    <keyword>use case</keyword>

    <abstract>
      <t>When an agent's output is presented to a user over time, as with
      synthesized speech, the agent has usually generated more than the user
      has received at the moment an exchange stops. Existing requirements
      cover abandoning an exchange and cancelling a task. They do not cover
      telling the participants in the dialog how much of the output the user
      actually received. This document describes one use case with two
      examples, a travel booking and a voice purchase, and derives five
      requirements that can be incorporated into the working group's use
      cases and requirements document.</t>
    </abstract>

    <note removeInRFC="true">
      <name>About This Document</name>
      <t>Discussion of this document takes place on the agentproto Working
      Group mailing list (<eref target="mailto:agentproto@ietf.org"/>), which
      is archived at
      <eref target="https://mailarchive.ietf.org/arch/browse/agentproto/"/>.
      The text was first sent to that list under the subject "Use case input:
      reporting how much output the user actually received" and revised
      there.</t>
    </note>
  </front>

  <middle>

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

      <t>The agentic AI use cases and requirements document <xref
      target="I-D.agentic-ai-usecases-requirements"/> requires incremental
      streaming of agent output (A1-1) and a task cancellation message
      (A1-2). The contact center use cases document <xref
      target="I-D.howe-agentproto-contact-center-usecases"/> adds identifiers
      for individual exchanges (CC4-2), a signal that an exchange in progress
      is abandoned, such as when a user interrupts synthesized speech
      (CC4-3), and receive-only participants such as a recorder (CC4-4).</t>

      <t>These requirements describe what was generated and when an exchange
      stopped. None of them tells the participants how much of the output
      had been presented to the user when it stopped. For text shown at once
      the difference is small. For speech it is not: presentation takes
      longer than generation, so an agent can have produced several
      sentences of which the user heard half of one.</t>

      <t>The gap matters to three kinds of participant. The agent that
      generated the output cannot resolve the user's next utterance if it
      does not know what the user heard. A recorder holds words the user
      never received. An agent that the first agent delegated to may treat
      information as disclosed to the user when it was not.</t>

      <t>This document proposes one use case and five requirements to close
      that gap. It is written as input to <xref
      target="I-D.agentic-ai-usecases-requirements"/> and follows that
      document's structure for a use case. The requirement identifiers used
      here (UP-1 to UP-5) are provisional and are for the editors to
      assign.</t>
    </section>

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

      <t>This document uses the terms Dialog, Dialog Context, Task Context,
      Task, Modality, Delegation and User as defined in <xref
      target="I-D.agentic-ai-usecases-requirements"/>, and the term exchange
      as used in requirement CC4-2 of <xref
      target="I-D.howe-agentproto-contact-center-usecases"/>: an individual
      unit within a dialog, such as a single utterance or turn. In
      addition:</t>

      <dl newline="false">
        <dt>Generating participant:</dt>
        <dd>The participant that produces the output of an exchange, such as
        an agent.</dd>

        <dt>Presenting participant:</dt>
        <dd>The participant that presents the output of an exchange to a
        user, such as a speech synthesizer, a voice assistant or a client
        application.</dd>

        <dt>Presentation point:</dt>
        <dd>The point in the output of an exchange up to which that output
        was presented to the user.</dd>
      </dl>

      <t>This document uses "is required to" in the way <xref
      target="I-D.agentic-ai-usecases-requirements"/> does, to state a
      requirement on the protocol to be designed. It does not use the key
      words of BCP 14.</t>
    </section>

    <section anchor="usecase">
      <name>Use Case: Interrupted Output Presented to a User</name>

      <section anchor="description">
        <name>Description</name>

        <t>An agent streams a spoken reply to a user through a presenting
        participant. Presentation takes longer than generation, so when the
        exchange stops, the agent has generated more than the user received.
        Two events cause this: the user interrupts, or the device does, for
        example when an alarm or a doorbell takes the audio output.</t>

        <t>The presenting participant is the only participant that knows
        where presentation stopped. In a simple deployment it is the client
        application. In the voice use case of <xref
        target="I-D.howe-agentproto-contact-center-usecases"/> it is a
        synthesizer that may be a separate service run by a different
        provider from the agent, with a recorder and other receive-only
        participants in the same dialog.</t>
      </section>

      <section anchor="flow">
        <name>Interaction Flow</name>

        <ol>
          <li>The generating participant streams the output of an exchange
          (A1-1). The exchange has an identifier (CC4-2).</li>
          <li>The presenting participant presents the output to the user as
          it arrives. Presentation lags generation.</li>
          <li>The user or the device interrupts. The presenting participant
          stops, and the exchange is abandoned (CC4-3).</li>
          <li>The presenting participant reports the presentation point for
          that exchange, or reports that it could not be determined.</li>
          <li>The report reaches the generating participant and the other
          authorized participants in the dialog, including receive-only
          participants (CC4-4).</li>
          <li>The dialog continues, or is later resumed (B1-6, CC3-1), from
          what the user received.</li>
        </ol>

        <t>Steps 4 and 5 are the ones that existing requirements do not
        cover.</t>
      </section>

      <section anchor="example-travel">
        <name>Example 1: Travel Booking</name>

        <ol>
          <li>The agent streams: "Your flight leaves at 6:40 from gate B12,
          and I have also moved your hotel booking to Friday."</li>
          <li>The user interrupts after "gate B12". The presenting
          participant stops, and the exchange is abandoned (CC4-3).</li>
          <li>
            <t>The agent, a recorder (CC4-4) and any agent it delegated to
            still hold the full text. Without more information:</t>
            <ul>
              <li>the user's next utterance, "yes, do that", cannot be
              resolved, because the agent does not know whether the user
              heard the hotel change;</li>
              <li>the recording shows words the user never heard;</li>
              <li>a delegated agent may treat the hotel change as disclosed
              to the user.</li>
            </ul>
          </li>
          <li>Later, the user returns after a device interruption and the
          dialog resumes (B1-6, CC3-1). The agent needs the point the user
          reached, not the full generated text, to continue from the right
          place.</li>
        </ol>
      </section>

      <section anchor="example-purchase">
        <name>Example 2: Voice Purchase</name>

        <t>This example was contributed by Francesco Marinoni Moretto.</t>

        <ol>
          <li>A user buys a product by voice through an assistant. The
          merchant's agent sends, and the assistant speaks: "This product
          may contain traces of nuts. It costs 24 euros and can be returned
          within 30 days. Shall I place the order?"</li>
          <li>The user interrupts after "This product may contain" and says
          "yes, order it". The assistant stops the audio, and the exchange
          is abandoned (CC4-3).</li>
          <li>
            <t>The merchant's agent and a recorder (CC4-4) still hold the
            full statement. Without more information:</t>
            <ul>
              <li>the merchant's agent treats the allergen notice, the price
              and the return terms as given to the user;</li>
              <li>the recording shows a statement the user did not hear,
              followed by "yes";</li>
              <li>a later review of the purchase cannot tell what the user
              had been told when agreeing.</li>
            </ul>
          </li>
          <li>With the report in UP-1 delivered as in UP-4, the merchant's
          agent can repeat the part that was not presented before it takes
          the order, and the recorder holds what was presented. If the
          assistant cannot tell where the audio stopped, the report says so
          (UP-5), and the record does not imply that the whole statement was
          presented.</li>
          <li>The same holds where the "yes" answers an authorization
          checkpoint (B2-5): the presentation point shows what was presented
          before that response.</li>
        </ol>

        <t>Where a seller needs to show what a consumer was told before
        agreeing, the record has to reflect what was presented, not what was
        generated. That is the reason the recorder needs the presentation
        point here. Consumer protection rules of this kind exist in several
        jurisdictions; <xref target="EU-CRD"/> and <xref target="EU-FIC"/>
        are examples.</t>
      </section>

      <section anchor="requirements">
        <name>Protocol Requirements</name>

        <t>The requirements below use the tags of <xref
        target="I-D.agentic-ai-usecases-requirements"/>. Each is followed by
        a note on why the existing requirements do not already cover it.</t>

        <dl newline="true">
          <dt>UP-1 (Dialog)</dt>
          <dd>
            <t>The protocol is required to allow the participant that
            presents output to a user to report, for an exchange, the point
            up to which that output was presented, referencing the exchange
            identifier (CC4-2).</t>
            <t>Not covered today: A1-1 covers delivery of partial output to
            the client, and CC4-2 identifies an exchange as a whole. Neither
            lets a participant say how much of the exchange reached the
            user.</t>
          </dd>

          <dt>UP-2 (Transport, Dialog)</dt>
          <dd>
            <t>When an exchange is abandoned (CC4-3), the report in UP-1 is
            required to be carried with, or immediately after, the abandon
            signal, without delaying that signal. This complements A1-1 and
            A1-2.</t>
            <t>Not covered today: CC4-3 bounds the latency of the abandon
            signal and A1-2 defines task cancellation. Both say that output
            stopped. Neither carries how much had been presented, nor
            relates that information to the signal in time.</t>
          </dd>

          <dt>UP-3 (Dialog)</dt>
          <dd>
            <t>The presentation point is required to be expressed in terms
            that the participant that generated the output can map to its
            own output, without knowledge of the presenting participant's
            internals. The representation of the point is left to the
            application.</t>
            <t>Not covered today: no existing requirement gives the
            generating and presenting participants a common reference to a
            point inside an exchange. Without one, a report from a
            synthesizer run by another provider cannot be interpreted by the
            agent.</t>
          </dd>

          <dt>UP-4 (Dialog)</dt>
          <dd>
            <t>The report is required to reach the participant that
            generated the output and the other authorized participants in
            the dialog, including receive-only participants (CC4-4), so that
            dialog context reflects what was presented rather than what was
            generated. This applies the dialog context preservation of A1-10
            to what was presented.</t>
            <t>Not covered today: CC4-4 delivers authorized dialog context
            and lifecycle events to receive-only participants, and A1-10 and
            CC4-1 preserve dialog context across a change of modality. The
            presentation point is not among the things they deliver, so a
            recorder or a delegated agent learns that an exchange was
            abandoned but not what the user had received.</t>
          </dd>

          <dt>UP-5 (Dialog)</dt>
          <dd>
            <t>The report is required to distinguish a known presentation
            point from one that could not be determined, in the way B3-10
            distinguishes a cancellation that took effect from one that
            could not be determined. Whether presented content counts as
            understood by the user is left to the application.</t>
            <t>Not covered today: B3-10 reports the outcome of a
            cancellation along a delegation chain. It says nothing about
            presentation to a user. Without UP-5, a missing report is
            indistinguishable from complete presentation.</t>
          </dd>
        </dl>

        <t>The use of UP-1 after an interruption also supports resumption
        (B1-6, CC3-1).</t>
      </section>
    </section>

    <section anchor="discussion">
      <name>Discussion</name>

      <section anchor="layer">
        <name>Dialog Layer or Application Layer</name>

        <t>The presentation point could be left to each application. The
        list discussion favoured the dialog layer, for this reason: the
        recipients named in UP-4, recorders and delegated agents, are the
        participants least likely to see application-layer messages. If the
        report were only an application-layer message, the receive-only
        participants would be the first to miss it. What the point means for
        the user stays with the application, as UP-5 says.</t>
      </section>

      <section anchor="dialog-context">
        <name>Relationship to Dialog Context</name>

        <t><xref target="I-D.agentic-ai-usecases-requirements"/> defines
        dialog context as the identifiers and lifecycle state needed to
        correlate and maintain a dialog, and excludes the content exchanged
        with AI models. The report in UP-1 is consistent with that
        definition. It is a reference to a point in an identified exchange,
        together with whether that point is known. It carries no content. A
        participant that already holds the content of the exchange can apply
        the point to it; a participant that does not hold the content learns
        nothing about it from the report.</t>
      </section>

      <section anchor="cancellation">
        <name>Relationship to Reporting the Outcome of a Cancellation</name>

        <t>In the discussion of the use cases document, one of its editors
        has raised reporting the outcome of a cancellation as a question for
        the working group. This use case is the user-facing part of that
        question. B3-10 covers whether a cancellation took effect. UP-1,
        UP-2 and UP-5 cover how much of the output had been presented to the
        user when it did. Since the report refers to an exchange, it applies
        whether a dialog carries one task or several.</t>
      </section>

      <section anchor="existing-work">
        <name>Relationship to Other Work</name>

        <t><xref target="I-D.liu-moq-live-agent-interaction"/> defines a
        barge-in signal from the client and an acknowledgement in which the
        agent gives the position where its output stopped. That is the
        generating side's view of where generation ended. The requirements
        here concern the opposite direction: the presenting side's view of
        where presentation to the user ended, and its delivery to the other
        participants in the dialog. The two are complementary.</t>

        <t><xref target="I-D.agentic-ai-usecases-requirements"/> places
        accountability and auditing out of scope. This document does not
        define an audit record. It asks only that the dialog carry the
        presentation point, so that any record a participant keeps can be
        accurate about what the user received.</t>
      </section>
    </section>

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

      <t>A presentation point describes user behaviour: it reveals when a
      user interrupted and how much the user listened to. It is to be
      delivered only to participants authorized to receive dialog context
      for that dialog, as UP-4 states, and it inherits the considerations
      for passive participants in <xref
      target="I-D.howe-agentproto-contact-center-usecases"/>.</t>

      <t>A report may be relied on later to show what a user was told. A
      presenting participant that reports a later point than the one
      actually reached makes a record claim more than the user received.
      The report therefore needs integrity protection and needs to be
      attributable to the participant that made it, using the protocol's
      mechanisms for authenticating participants and protecting dialog
      context. A participant that receives a report can check only that the
      point lies within the output of the exchange; it cannot check that
      the user perceived the output, which is why UP-5 leaves that question
      to the application.</t>

      <t>UP-2 requires that the report not delay the abandon signal. An
      implementation that waited for an exact presentation point before
      signalling abandonment would weaken the bounded latency that CC4-3
      asks for.</t>
    </section>

    <section anchor="iana">
      <name>IANA Considerations</name>
      <t>This document has no IANA actions.</t>
    </section>

  </middle>

  <back>
    <references>
      <name>Informative References</name>

      <reference anchor="I-D.agentic-ai-usecases-requirements" target="https://datatracker.ietf.org/doc/html/draft-agentic-ai-usecases-requirements-07">
        <front>
          <title>Agentic AI Use Cases and Requirements</title>
          <author initials="T." surname="Reddy" fullname="T. Reddy"/>
          <author initials="Z." surname="Sarker" fullname="Z. Sarker"/>
          <author initials="K." surname="Yao" fullname="K. Yao"/>
          <date year="2026" month="November" day="2"/>
        </front>
        <seriesInfo name="Internet-Draft" value="draft-agentic-ai-usecases-requirements-07"/>
        <refcontent>Work in Progress</refcontent>
      </reference>

      <reference anchor="I-D.howe-agentproto-contact-center-usecases" target="https://datatracker.ietf.org/doc/html/draft-howe-agentproto-contact-center-usecases-00">
        <front>
          <title>Contact Center Use Cases and Requirements for Agentic Dialogs</title>
          <author initials="T." surname="Howe" fullname="Thomas Howe"/>
          <date year="2026" month="October" day="25"/>
        </front>
        <seriesInfo name="Internet-Draft" value="draft-howe-agentproto-contact-center-usecases-00"/>
        <refcontent>Work in Progress</refcontent>
      </reference>

      <reference anchor="I-D.liu-moq-live-agent-interaction" target="https://datatracker.ietf.org/doc/html/draft-liu-moq-live-agent-interaction-02">
        <front>
          <title>Live Agent Interaction over MoQ</title>
          <author initials="Y." surname="Liu" fullname="Y. Liu"/>
          <author initials="D." surname="Liu" fullname="D. Liu"/>
          <date year="2026" month="September" day="27"/>
        </front>
        <seriesInfo name="Internet-Draft" value="draft-liu-moq-live-agent-interaction-02"/>
        <refcontent>Work in Progress</refcontent>
      </reference>

      <reference anchor="EU-CRD" target="https://eur-lex.europa.eu/eli/dir/2011/83/oj">
        <front>
          <title>Directive 2011/83/EU of the European Parliament and of the Council of 25 October 2011 on consumer rights, Articles 6 and 8(2)</title>
          <author>
            <organization>European Union</organization>
          </author>
          <date year="2011" month="October"/>
        </front>
      </reference>

      <reference anchor="EU-FIC" target="https://eur-lex.europa.eu/eli/reg/2011/1169/oj">
        <front>
          <title>Regulation (EU) No 1169/2011 of the European Parliament and of the Council of 25 October 2011 on the provision of food information to consumers, Article 14</title>
          <author>
            <organization>European Union</organization>
          </author>
          <date year="2011" month="October"/>
        </front>
      </reference>
    </references>

    <section anchor="acknowledgements" numbered="false">
      <name>Acknowledgements</name>

      <t>Francesco Marinoni Moretto contributed the voice purchase example,
      the consumer protection references and the argument for placing the
      report in the dialog layer. Konrad Gruszka pointed out the link to
      authorization checkpoint responses (B2-5). Both reviewed the text on
      the agentproto mailing list.</t>
    </section>
  </back>
</rfc>
