---
schema_version: "1"
id: 1f773d23a46ec148b1f146dc3018b23f989f677cd9576f5969c4480f87143f8d
title: Considerations for the Journey Decisioning Agent in Marketing Cloud Next
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/mktg/264-0-0/mktg_einstein_journey_decisioning_considerations.md
canonical_url: https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_journey_decisioning_considerations.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 0ed7e879c16ba7035526748295d923d3f1e277a6051c056878da153e501fb22c
description: To use the Journey Decisioning agent, consider supported functionality, usage, limitations and allowances, limits, and other issues.
products:
  - Marketing
release: "264"
---
# Considerations for the Journey Decisioning Agent in Marketing Cloud Next

To use the Journey Decisioning agent, consider supported functionality, usage, limitations and allowances, limits, and other issues.

[View supported editions](https://help.salesforce.com/s/articleView?id=mktg.mktg_editions.htm&release=264.0.0&type=5 "Marketing Cloud Next is available in Growth and Advanced editions, and requires Salesforce Enterprise or Unlimited editions. Some features are limited by edition or purchased add-on. All functionality is available in Lightning Experience only.").

## Language and Locale Support

The Journey Decisioning agent supports the languages and locales supported on the Salesforce generative AI platform, as described in [Einstein Generative AI Supported Languages and Locales](https://help.salesforce.com/s/articleView?id=ai.generative_ai_platform_languages.htm&language=en_US).

## Large Language Model Support

The Journey Decisioning agent supports the models on the Salesforce generative AI platform, as described in [Large Language Model Support](https://help.salesforce.com/s/articleView?id=ai.generative_ai_large_language_model_support.htm&language=en_US). By default, calls use OpenAI GPT-4o.

## Einstein Trust Layer Service Support

The Journey Decisioning agent supports the Trust Layer services provided on the Saleforce generative AI platform, as described in [Einstein Trust Layer](https://help.salesforce.com/s/articleView?id=ai.generative_ai_trust_layer.htm&language=en_US). Ask your system administrator about which Einstein Trust Layer services are enabled in your org and available for the Journey Decisioning Agent.

## Feature Region Support

The Journey Decisioning agent supports the geo-aware models supported on the Salesforce generative AI platform, as described in [Geo-Aware LLM Request Routing on the Einstein Generative AI Platform](https://help.salesforce.com/s/articleView?id=ai.generative_ai_platform_geo_aware_routing.htm&language=en_US).

## Usage Types Consumed by Journey Decisioning

The Journey Decisioning agent uses generative AI and Data 360 to ingest, store, and process data. You’re billed in these categories when you use the Journey Decisioning agent. Before deployment, work with your Salesforce account team to confirm license availability and plan credit usage.

![Tip](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-mktg-mktg_all-264-0-0-production-enus/e92be4e1-4bef-47a5-a11d-95f4ea1f7d7a/images/icon_tip.png)

Tip

This feature has access to Digital Wallet, a free account management tool that offers near real-time consumption data for enabled products across your active contracts. Access Digital Wallet and start tracking your org's usage. To learn more, see [About Digital Wallet](https://help.salesforce.com/s/articleView?id=xcloud.wallet_about.htm&language=en_US&type=5).

## Flex Credits

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small ">
        <colgroup>
          <col style="width:20%">
          <col style="width:80%">
        </colgroup>
        <thead class="slds-text-title_caps ">
          <tr class="">
            <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d86433e127">Usage Type / Subtype</th>
            <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d86433e130">Description</th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e936" style="vertical-align:top;" headers="d86433e127 ">Standard Action</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e939" style="vertical-align:top;" headers="d86433e130 ">
              <p>Usage is determined by the number of standard actions called by the agent in a text
                conversation. Currently, every standard action called by the agent is metered as one
                standard action, irrespective of the number of tokens processed. </p>
              <p>Standard agent actions are actions that are available out-of-the-box. To check the list
                of Standard actions, see <a href="https://help.salesforce.com/s/articleView?id=ai.copilot_actions_ref.htm&amp;type=5&amp;language=en_US" target="_blank"><u>Standard Action Reference</u></a>.</p>
              <div>
                <div class="slds-box slds-box_x-small slds-theme_shade slds-m-top_medium slds-m-bottom_medium">
                  <div class="slds-media slds-media_responsive">
                    <div class="slds-media__figure"><span class="slds-icon_container slds-icon_container_circle slds-icon-note-note"><img style="margin-bottom:0;" src="https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-mktg-mktg_all-264-0-0-production-enus/e92be4e1-4bef-47a5-a11d-95f4ea1f7d7a/images/icon_note.png" alt="Note"></span></div>
                    <div class="slds-media__body" style="padding-top:.5rem;padding-bottom:.5rem;"><span class="slds-text-title_caps">Note</span> Use of some standard agent actions require that a subscription has been purchased for
                      each user that accesses these actions, such as a subscription to Agentforce for Sales
                      Add-on or Agentforce for Service Add-on. To determine which subscription is required for
                      such standard actions, see Standard Action Reference at <a href="https://help.salesforce.com/s/articleView?id=ai.copilot_actions_ref.htm&amp;type=5&amp;language=en_US" target="_blank"><u>Standard Action Reference</u></a>. While this
                      requirement is not technically enforced yet, users who don’t have the required add-on
                      license will lose access to such actions for which they don’t have a license when the
                      requirement is enforced.</div>
                  </div>
                </div>
              </div>
            </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e965" style="vertical-align:top;" headers="d86433e127 ">Custom Action</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e968" style="vertical-align:top;" headers="d86433e130 ">
              <p>Usage is determined by the number of custom actions called by the agent in a text
                conversation. Currently, every custom action called by the agent is metered as one custom
                action, irrespective of the number of tokens processed. </p>
              <p style="margin-bottom:0;">Async calls to Salesforce AI in custom action implementation may incur additional
                charges.</p>
            </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e980" style="vertical-align:top;" headers="d86433e127 ">Standard Voice Action</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e983" style="vertical-align:top;" headers="d86433e130 ">
              <p>Usage is determined by the number of standard actions executed by the agent in a voice
                conversation.</p>
              <div class="slds-box slds-box_x-small slds-theme_shade slds-m-top_medium slds-m-bottom_medium">
                <div class="slds-media slds-media_responsive">
                  <div class="slds-media__figure"><span class="slds-icon_container slds-icon_container_circle slds-icon-note-note"><img style="margin-bottom:0;" src="https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-mktg-mktg_all-264-0-0-production-enus/e92be4e1-4bef-47a5-a11d-95f4ea1f7d7a/images/icon_note.png" alt="Note"></span></div>
                  <div class="slds-media__body" style="padding-top:.5rem;padding-bottom:.5rem;"><span class="slds-text-title_caps">Note</span> Use of some standard agent actions require that a subscription has been purchased for
                    each user that accesses these actions, such as a subscription to Agentforce for Sales
                    Add-on or Agentforce for Service Add-on. To determine which subscription is required for
                    such standard actions, see Standard Action Reference at <a href="https://help.salesforce.com/s/articleView?id=ai.copilot_actions_ref.htm&amp;type=5&amp;language=en_US" target="_blank"><u>Standard Action Reference</u></a>. While this
                    requirement is not technically enforced yet, users who don’t have the required add-on
                    license will lose access to such actions for which they don’t have a license when the
                    requirement is enforced.</div>
                </div>
              </div>
            </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e999" style="vertical-align:top;" headers="d86433e127 ">Custom Voice Action</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1002" style="vertical-align:top;" headers="d86433e130 ">
              <p>Usage is determined by the number of custom
                actions called by the agent in a voice conversation. </p>
              <p dir="ltr">Custom actions are actions
                that are created by you or which result from your modification of a standard action. To
                learn more about what customer created actions are, see <a href="https://help.salesforce.com/s/articleView?id=ai.copilot_actions_custom.htm&amp;type=5&amp;language=en_US" target="_blank"><u>Create a Custom Agent Action</u></a>. To learn more
                about how standard actions become custom actions, see <a href="https://help.salesforce.com/s/articleView?id=ai.copilot_actions_edit_reference.htm&amp;type=5&amp;language=en_US" target="_blank"><u>Editing Standard Agent Action Reference
                    Actions</u></a>.</p>
              <p style="margin-bottom:0;">Async calls to Salesforce AI in custom action implementation
                may incur additional charges.</p>
            </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1020" style="vertical-align:top;" headers="d86433e127 ">Starter Prompts</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1023" style="vertical-align:top;" headers="d86433e130 ">
              <p>Usage is calculated based on two factors: the number
                of direct requests to the LLM via the LLM gateway, and whether the gateway uses a Bring Your
                Own Large Language Model (BYOLLM).</p>
              <p>Each starter prompt includes the processing of up to
                2,000 tokens. Prompt usage is counted in chunks of 2,000 tokens, rounded up. Prompts that
                exceed this limit will be metered as multiple prompts, with each additional 2,000-token
                chunk counting as a new prompt. For example, a prompt with a total of 6,500 input and
                output tokens will be metered as 4 prompts.</p>
              <p style="margin-bottom:0;">Tokens are units of data processed by the
                AI models.</p>
            </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1034" style="vertical-align:top;" headers="d86433e127 ">
              <p>Standard Prompts</p>
              <p>Basic Prompts</p>
              <p style="margin-bottom:0;">Advanced Prompts</p>
            </td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1046" style="vertical-align:top;" headers="d86433e130 ">
              <p>Usage is calculated based on two factors:
                the number of direct requests to the LLM via the LLM gateway, and whether the gateway uses a
                Salesforce managed large language model. The specific category depends on the model that is
                used. See Large <a href="https://help.salesforce.com/s/articleView?id=ai.generative_ai_large_language_model_support.htm&amp;language=en_US" target="_blank">Language Model Support</a> to find out which usage types
                apply. </p>
              <p>All Standard, Basic, and Advanced prompts process up to 2,000 tokens per prompt.
                Token usage is rounded up in 2,000-token increments. All Standard, Basic, and Advanced
                prompts that exceed this limit will be metered as multiple prompts, with each additional
                2,000-token chunk counting as a new prompt. For example, a prompt with a total of 6,500
                input and output tokens will be metered as 4 prompts. </p>
              <p>Tokens are units of data
                processed by the AI models. </p>
              <div>
                <div class="slds-box slds-box_x-small slds-theme_shade slds-m-top_medium slds-m-bottom_medium">
                  <div class="slds-media slds-media_responsive">
                    <div class="slds-media__figure"><span class="slds-icon_container slds-icon_container_circle slds-icon-note-note"><img style="margin-bottom:0;" src="https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-mktg-mktg_all-264-0-0-production-enus/e92be4e1-4bef-47a5-a11d-95f4ea1f7d7a/images/icon_note.png" alt="Note"></span></div>
                    <div class="slds-media__body" style="padding-top:.5rem;padding-bottom:.5rem;"><span class="slds-text-title_caps">Note</span> Advanced Prompts were launched with a designated multiplier listed in the Agentforce
                      <a href="https://www.salesforce.com/agentforce/rates/" target="_blank">Flex Credits Rate Card</a>. Salesforce will start metering the use of Advanced
                      Prompts on July 21, 2026.
                    </div>
                  </div>
                </div>
              </div>
            </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1067" style="vertical-align:top;" headers="d86433e127 ">Translation</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1070" style="vertical-align:top;" headers="d86433e130 ">
              <p>Translation converts text from one human language into
                text of another, a process executed by machine translation models. Translation usage is
                metered by the number of characters processed for the translation. </p>
              <p style="margin-bottom:0;">To understand how your
                consumption appears in the Digital Wallet, consider a scenario where you process 9,000
                characters for translation. Because this usage is in units of one million characters, your
                actual consumption is 0.009 units (9,000 divided by 1,000,000). In the Digital wallet, this
                usage is rounded to two decimal places and the value is displayed as 0.01 units.
              </p>
            </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1078" style="vertical-align:top;" headers="d86433e127 ">Agentforce Voice Minutes</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1081" style="vertical-align:top;" headers="d86433e130 ">
              <p>Usage is determined by the duration of the
                voice call between an end user and Agentforce Voice. Usage is rounded up to the next full
                minute, meaning any fraction of a minute is treated as a full minute. </p>
              <p>For example, </p>
              <ul>
                <li>A call of 60 seconds is billed as 1 minute. </li>

                <li>A call of 61 seconds is billed as 2 minutes.</li>

              </ul>
              <p style="margin-bottom:0;">If your org has both Agentforce Voice Actions and Agentforce Voice Minutes enabled,
                Voice Minutes take precedence for billing. When Agentforce Voice Minutes are available in
                your org, only Agentforce Voice Minutes are metered, and Voice Actions usage types are not
                applied to the same activity. </p>
            </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1099" style="vertical-align:top;" headers="d86433e127 ">Speech-to-Text</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1102" style="vertical-align:top;" headers="d86433e130 ">Speech-to-Text converts spoken audio into written
              text, a process run by automatic speech recognition (ASR) models. Usage is calculated based
              on the duration of the audio processed for each transcription, in seconds. In Digital
              Wallet, this usage is aggregated and displayed in minutes. </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1108" style="vertical-align:top;" headers="d86433e127 ">Text-to-Speech</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1111" style="vertical-align:top;" headers="d86433e130 ">
              <p>Text-to-Speech converts written text into
                natural-sounding spoken audio, a process run by automatic Speech Synthesis models. Usage is
                metered by the number of text characters processed for the speech generation. In the Digital
                Wallet, this usage is aggregated and displayed in units of million characters. </p>
              <p style="margin-bottom:0;">To
                understand how your consumption appears in the Digital Wallet, consider a scenario where
                you process 9,000 characters for conversion from text to speech. Because this usage is in
                units of one million characters, your actual consumption is 0.009 units (9,000 divided by
                1,000,000). In the Digital wallet, this usage is rounded to two decimal places and the
                value is displayed as 0.01 units.</p>
            </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" style="vertical-align:top;" headers="d86433e127 ">&nbsp;</td>

            <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d86433e130 ">&nbsp;</td>

          </tr>

          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1127" style="vertical-align:top;" headers="d86433e127 ">Email</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1130" style="vertical-align:top;" headers="d86433e130 ">Usage is calculated based on the number of
              interactions resolved by Help Agent through email.</td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1136" style="vertical-align:top;" headers="d86433e127 ">Enhanced Chat &amp; Portal</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1139" style="vertical-align:top;" headers="d86433e130 ">
              <p style="margin-bottom:0;">Usage is calculated based on the number of interactions resolved by Help Agent through
                Enhanced Chat or a portal. A resolution is defined as up to 2 hours of interaction. If the
                user interacts with the agent for more than 2 hours, it is counted as a second resolution.
              </p>
            </td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1148" style="vertical-align:top;" headers="d86433e127 ">Third-Party Messaging Channels</td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1151" style="vertical-align:top;" headers="d86433e130 ">Usage is calculated based on the number of interactions resolved by Help Agent through
              third-party messaging channels such as WhatsApp, Facebook Messenger, or SMS. A resolution is
              defined as up to 2 hours of interaction. If the interaction exceeds 2 hours, it is counted
              as a second resolution.</td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1157" style="vertical-align:top;" headers="d86433e127 ">Voice Channel </td>

            <td data-label="Description" class="slds-cell-wrap" id="mktg_einstein_journey_decisioning_considerations__d404e1160" style="vertical-align:top;" headers="d86433e130 ">Usage is calculated based on the number of
              interactions resolved by Help Agent through a voice call. The duration limit for a single
              resolution is 10 minutes. Calls extending beyond 10 minutes are counted as multiple
              resolutions (for example, a 12-minute call is counted as 2 resolutions when
              resolved).</td>

          </tr>
          <tr class="">
            <td data-label="Usage Type / Subtype" class="slds-cell-wrap" style="vertical-align:top;" headers="d86433e127 ">&nbsp;</td>

            <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d86433e130 ">&nbsp;</td>

          </tr>
        </tbody>
      </table>

When you use the Journey Decisioning agent, credits can be consumed in usage types on other consumption cards by related features such as [Agentforce Data Library](https://help.salesforce.com/s/articleView?id=ai.data_library_parent.htm&language=en_US), [Audit and Feedback](https://help.salesforce.com/s/articleView?id=ai.generative_ai_audit_feedback_usage_types.htm&language=en_US), or [Data 360 Billable Usage Types](https://help.salesforce.com/s/articleView?id=data.c360_a_data_usage_types.htm&language=en_US).

## Data Cloud One Support

The Journey Decisioning agent isn't supported in Data Cloud One companion orgs.

## Associated Standard Actions

These standard actions are associated with the Journey Decisioning agent.

- Marketing Cloud: Select Journey
- Marketing Cloud: Create Journey Content