---
schema_version: "1"
id: 7bc320ab6eca2b06adca81092231ef3466ac744b723de10086693eeef98b31a5
title: Einstein Trust Layer Service Support
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/cc/264-0-0/b2c_shopper_agent_trust_layer_support.md
canonical_url: https://help.salesforce.com/s/articleView?id=cc.b2c_shopper_agent_trust_layer_support.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: a09a44237a14a7aa9b53c0fee8cdcc9457464aea0259c0fee7a23e768b8e853f
description: The Shopper Agent for B2C Commerce supports these trust layer services.
products:
  - Commerce
  - B2C Commerce
release: "264"
---
# Einstein Trust Layer Service Support

The Shopper Agent for B2C Commerce supports these trust layer services.

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small ">
      <colgroup>
        <col>
        <col>
      </colgroup>
      <thead class="slds-text-title_caps ">
        <tr class="">
          <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d104952e36">Service</th>
          <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d104952e39">Description</th>
        </tr>
      </thead>
      <tbody>
        <tr class="">
          <td data-label="Service" class="slds-cell-wrap" style="vertical-align:top;" headers="d104952e36 ">Zero Data Retention Policy</td>

          <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d104952e39 ">
            <p>Your data isn’t retained by third-party LLMs. We partner with all our external
              model providers, such as OpenAI, to enforce the zero-data retention policy.</p>
            <ul>
              <li> No data is used for LLM model training or product improvements by third-party
                LLMs.</li>

              <li>No data is retained by the third-party LLMs.</li>

              <li>No human being at the third-party provider looks at data sent to their
                LLM.</li>

            </ul>
          </td>

        </tr>
        <tr class="">
          <td data-label="Service" class="slds-cell-wrap" style="vertical-align:top;" headers="d104952e36 ">Dynamic Grounding with Secure Data Retrieval</td>

          <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d104952e39 ">
            <p>
              <strong>
                <a href="https://help.salesforce.com/s/articleView?id=ai.generative_ai_trust_arch.htm&amp;type=5&amp;language=en_US" target="_blank">Dynamic Grounding with Secure Data Retrieval
                </a>
              </strong>
            </p>
            <ul>
              <li> Relevant information from a Salesforce record is merged with the prompt to
                provide context. </li>

              <li>Secure data retrieval of Salesforce data for grounding the prompt based on the
                permissions of the user executing the prompt.</li>

              <li>Secure data retrieval preserves in place all standard Salesforce role-based
                controls for user permissions and field-level security when merging grounding
                data from your CRM instance or Data 360.</li>

            </ul>
          </td>

        </tr>
        <tr class="">
          <td data-label="Service" class="slds-cell-wrap" style="vertical-align:top;" headers="d104952e36 ">Prompt Defense</td>

          <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d104952e39 ">
            <ul>
              <li>System policies help limit hallucinations and decrease the likelihood of
                unintended or harmful outputs by the LLM.</li>

              <li>System policies can vary for different generative AI features and use
                cases.</li>

            </ul>
          </td>

        </tr>
        <tr class="">
          <td data-label="Service" class="slds-cell-wrap" style="vertical-align:top;" headers="d104952e36 ">Toxicity Detection</td>

          <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d104952e39 ">
            <ul>
              <li>Einstein Trust Layer scores content on toxicity.</li>

              <li>Toxicity scores are logged and stored in Data 360 as part of the audit
                trail.</li>

            </ul>
            <p style="margin-bottom:0;">The service detects and flags potentially harmful LLM responses.</p>
          </td>

        </tr>
        <tr class="">
          <td data-label="Service" class="slds-cell-wrap" style="vertical-align:top;" headers="d104952e36 ">Audit</td>

          <td data-label="Description" class="slds-cell-wrap" style="vertical-align:top;" headers="d104952e39 ">
            <ul>
              <li>Prompts, responses, and trust signals are logged and stored in <span>Data 360</span>.</li>

              <li>Feedback can be used for improving prompt templates.</li>

              <li>Provides pre-built reports and dashboards for analysis.</li>

            </ul>
          </td>

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

![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-cc-b2c_merchandiser_administrator-264-0-0-production-enus/ea76f372-6cfa-42a6-8e7c-05c6df7abed8/images/icon_note.png)

Note Data masking through the Einstein Trust Layer is disabled to improve the performance and accuracy of agents. Ask your Salesforce admin which Einstein Trust Layer services are enabled in your org and available for the Shopper Agent.