---
schema_version: "1"
id: c0ed553ecda572bb35f5b149fb5ab95edee8f65b2eed21938a14a021c18cb9ca
title: Use the Predictive Model Agent Reference Action to Enhance Predictions
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/data/264-0-0/c360_a_ai_predictive_model_reference_action.md
canonical_url: https://help.salesforce.com/s/articleView?id=data.c360_a_ai_predictive_model_reference_action.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 1c9acbecb233ef8bdbeba0f48f6055dfa5742a87c5ad02ae001cf921b6c59f47
description: For an AI agent to provide and interpret outputs from a predictive model, you must create a custom agent action in your org. Let's look at how Agentforce can enhance predictions from a Predicted Attrition model that was created in Model Builder.
products:
  - Data 360
release: "264"
---
# Use the Predictive Model Agent Reference Action to Enhance Predictions

For an AI agent to provide and interpret outputs from a predictive model, you must create a custom agent action in your org. Let's look at how Agentforce can enhance predictions from a Predicted Attrition model that was created in Model Builder.

### Required Editions

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small edition"><colgroup><col></colgroup><tbody><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;">Available in: <strong>All Editions</strong> supported by Data 360. See <a href="https://help.salesforce.com/s/articleView?id=data.c360_a_dc_editions.htm&amp;language=en_US" target="_blank">Data 360 edition availability</a>.</td></tr></tbody></table>

For editions and permissions needed to create a custom agent action, see [Agent Actions](https://help.salesforce.com/s/articleView?id=ai.copilot_actions.htm&language=en_US).

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small permission">
        <colgroup>
          <col style="width:50%">
          <col style="width:50%">
        </colgroup>
        <thead class="slds-text-title_caps ">
          <tr class="">
            <th scope="colgroup" class="slds-cell-wrap" colspan="2" style="text-align:center;vertical-align:top;" id="d179453e61">USER PERMISSIONS
              NEEDED</th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="USER PERMISSIONS NEEDED" class="slds-cell-wrap" style="vertical-align:top;" headers="d179453e61 ">Allow users to manage models in AI Models</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d179453e61 ">Enables you to create, update, and delete models in AI Models.</td>

          </tr>
        </tbody>
      </table> <table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small permission">
        <colgroup>
          <col style="width:50%">
          <col style="width:50%">
        </colgroup>
        <thead class="slds-text-title_caps ">
          <tr class="">
            <th scope="colgroup" class="slds-cell-wrap" colspan="2" style="text-align:center;vertical-align:top;" id="d179453e91">PERMISSION SETS </th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="PERMISSION SETS" class="slds-cell-wrap" style="vertical-align:top;" headers="d179453e91 ">Data Cloud Architect</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d179453e91 ">Admin-level access to all AI Models features, including the ability to create,
              update, delete, and activate models.</td>

          </tr>
          <tr class="">
            <td data-label="PERMISSION SETS" class="slds-cell-wrap" style="vertical-align:top;" headers="d179453e91 ">Data Cloud User</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d179453e91 ">Restricted access to use a model, including getting predictions and
              improvements derived from a model.</td>

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

1. From Setup, search for and select **Agentforce Assets**.
2. Go to the Actions tab and click **New Agent Action**.
    
    ![Agentforce Asset Library displaying the option to create a new agent action.](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-data-data_cloud-264-0-0-production-enus/f3569962-3c9b-4f83-9d0c-b6a574e785da/data_cloud/images/c360_a_ai_agentforce_new_agent_action.png)
3. Select the Predictive Model reference action type.
    
    ![Modal to create a new agent action.](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-data-data_cloud-264-0-0-production-enus/f3569962-3c9b-4f83-9d0c-b6a574e785da/data_cloud/images/c360_a_ai_agentforce_create_agent_action.png)
4. For the reference action, select the model (Predicted Attrition) that you want the agent to provide predictions for. The agent action label and API name is autopopulated.
    
    ![Important](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-data-data_cloud-264-0-0-production-enus/f3569962-3c9b-4f83-9d0c-b6a574e785da/images/icon_important.png)
    
    Important Only models that are activated in AI Models are displayed.
5. Click **Next**.
6. Review and update the Predicted Attrition agent action. If needed, you can customize the pre-populated text.
    
    ![Modal to create an agent action and its configuration.](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-data-data_cloud-264-0-0-production-enus/f3569962-3c9b-4f83-9d0c-b6a574e785da/data_cloud/images/c360_a_ai_agentforce_agent_action_configuration.png)
    
    1. Agent Action Instructions (pre-populated text):
        
        Requests a predictive model to return outputs based on the run-time values of input variables. These values originate from the agent's context, such as from records or user inputs. For a regression model, this action returns a numeric value for a predicted outcome, such as expected deal revenue. For a binary classification model, this action returns a numeric score indicating the likelihood of an outcome, such as lead conversion. No-code models built with Model Builder also provide top predictive factors and prescriptions to optimize the predicted outcome.
    2. Inputs: Each field in the model schema is displayed as an input, and some fields are model variables.
        
        Autopopulated text is used for these model inputs.
        
        ![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-data-data_cloud-264-0-0-production-enus/f3569962-3c9b-4f83-9d0c-b6a574e785da/images/icon_note.png)
        
        Note
        
        The _Require Input_ option is selected for all inputs except for Recommendations.
        
        i. **Top Predictors** — specify the number of outputs. If no value is specified, the default is 3.
        
        ii. **Recommendations** — specify the number of outputs. If no value is specified, the default is 3.
        
        iii. **Department** — the model requires a value for Department. Get the value at run time from a record, a user conversation, or some other source.
        
        iv. **Daily Rate** — the model requires a value for Daily Rate. Get the value at run time from a record, a user conversation, or some other source.
        
        v. **Age** — the model requires a value for Age. Get the value at run time from a record, a user conversation, or some other source.
        
        vi. **Total Working Years** — the model requires a value for Total Working Years. Get the value at run time from a record, a user conversation, or some other source.
        
        vii. **Years at Company** — the model requires a value for Years At Company. Get the value at run time from a record, a user conversation, or some other source.
    3. Outputs: Results provided by the predictive model.
        
        Autopopulated text is used for these model outputs.
        
        i. **Top Predictors** — represents the most important variables that influence a predictive outcome. The Output Rendering option is an Apex class type.
        
        ii. **Recommendations** — represents actions that can improve a predicted outcome. The Output Rendering option is an Apex class type.
        
        iii. **Prediction** — represents a prediction. The meaning of the value depends on the model type. The Output Rendering option is a decimal.
    4. When your agent action settings are complete, click **Finish**. The Predicted Attrition action must be assigned to an active agent such as Predictive Assistant.
        
        ![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-data-data_cloud-264-0-0-production-enus/f3569962-3c9b-4f83-9d0c-b6a574e785da/images/icon_note.png)
        
        Note
        
        You must select the _Show In Conversation_ option for at least one output.
7. In Agentforce Builder, create a new topic to assign to an agent action based on the model's outcome, and click **Next**.
    
    You can ask a question based on the model outcome, such as: what’s the likelihood that customers will switch brands?
    
    ![Agentforce Builder modal for creating a new Predictive Assistant topic.](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-data-data_cloud-264-0-0-production-enus/f3569962-3c9b-4f83-9d0c-b6a574e785da/data_cloud/images/c360_a_ai_agentforce_builder_predictive_assistant_new_topic.png)
8. Review the autopopulated topic fields. Update the information as needed, and if you're satisfied, click **Next**.
9. Click **Finish** to assign your agent action to the topic. Now you can use the action so the agent can provide responses from the model.
10. Click the topic and use the conversation preview to post questions related to the model outcome.
    
    ![Agentforce Builder displaying topic settings for the Predictive Assistant prior to activation.](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-data-data_cloud-264-0-0-production-enus/f3569962-3c9b-4f83-9d0c-b6a574e785da/data_cloud/images/c360_a_ai_agentforce_builder_predictive_assistant_test.png)
11. Activate the topic you’re satisfied with the responses provided by your agent.