---
schema_version: "1"
id: eb4b21d8f7b82d08d0098e75bd22ed35c1cf3f48e79193da46130def971129de
title: Share Insights from Einstein Generative AI Audit and Feedback Data
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/ai/264-0-0/generative_ai_feedback_analytics.md
canonical_url: https://help.salesforce.com/s/articleView?id=ai.generative_ai_feedback_analytics.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: b580254752358139e0386d177f11f7312c1b606ee00ca006a6858adf1fd437a0
description: Share insights from your org’s Einstein generative AI audit and feedback data with your team. Use pre-built dashboards and reports, running queries, and building Data 360 reports.
products:
  - Agentforce
  - Cross Cloud
release: "264"
---
# Share Insights from Einstein Generative AI Audit and Feedback Data

Share insights from your org’s Einstein generative AI audit and feedback data with your team. Use pre-built dashboards and reports, running queries, and building Data 360 reports.

### 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>Enterprise</strong>, <strong>Performance</strong>, and <strong>Unlimited</strong> Editions with an Einstein for Sales, Einstein for Platform, Einstein for Service, Einstein 1 Service, or Einstein GPT Service add-on. To purchase add-ons, contact your Salesforce account executive.</td></tr></tbody></table>

## Use Pre-Built Dashboards and Reports

Use the pre-built Data 360 dashboards to:

- analyze the generative AI, and
- share insights such as data masking, toxicity in responses, user trends, acceptance rates, and response feedback.

![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/images/icon_note.png)

Note When you turn on Einstein Generative AI Audit and Feedback for the first time, it can take a few minutes before you can access the pre-built reports and dashboards. If Audit and Feedback is turned on but you don't see the reports and dashboards, go to Setup and turn off [Audit and Feedback](https://help.salesforce.com/s/articleView?id=ai.generative_ai_feedback_enable.htm&release=264.0.0&type=5 "To collect Einstein generative AI audit and feedback data, turn it on in Einstein Setup. For orgs with only one dataspace, it’s turned on by default when Agentforce is turned on."), then turn it back on again.

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small ">
        <colgroup>
          <col style="width:24.509803921568626%">
          <col style="width:75.49019607843137%">
        </colgroup>
        <thead class="slds-text-title_caps ">
          <tr class="">
            <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d222720e86">Dashboard Name</th>
            <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d222720e89">What You Can Do with It</th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="Dashboard Name" class="slds-cell-wrap" style="vertical-align:top;" headers="d222720e86 ">Einstein Generative AI and Feedback Data</td>

            <td data-label="What You Can Do with It" class="slds-cell-wrap" style="vertical-align:top;" headers="d222720e89 ">
              <p>Monitor the use of generative AI within your Salesforce org. Analyze user
                feedback, token consumption, request counts, and user engagement weekly. The
                dashboard provides visualizations for: </p>
              <ul>
                <li>Weekly count of users engaging with generative AI features.</li>

                <li>Weekly count of requests made to the large language model (LLM).</li>

                <li>Total number of user feedback events collected, classified by feature.</li>

                <li>Weekly token usage.</li>

              </ul>
              <p>To see more detailed information, refer to the reports linked in the charts.
              </p>
              <p style="margin-bottom:0;">The Einstein Generative AI and Feedback Data dashboard is a standard
                dashboard. </p>
            </td>

          </tr>
          <tr class="">
            <td data-label="Dashboard Name" class="slds-cell-wrap" style="vertical-align:top;" headers="d222720e86 ">Einstein Trust Layer </td>

            <td data-label="What You Can Do with It" class="slds-cell-wrap" style="vertical-align:top;" headers="d222720e89 ">
              <p>Monitor Einstein Trust Layer metrics such as data masking and toxicity.
                Identify any concerning patterns or trends by using this dashboard. The dashboard
                contains visualizations for:</p>
              <ul>
                <li>Data masking trends over the past 7 days, 30 days, and for all time. </li>

                <li>Data masking trends by feature over the past 7 days, 30 days, and for all
                  time. </li>

                <li>Trends in toxic responses were categorized over the past 7 days, 30 days, and
                  for all time. </li>

                <li>Trends in toxic responses by feature over the past 7 days, 30 days, and for
                  all time.</li>

              </ul>
              <p>For further details, refer to the reports linked in the charts. </p>
              <p style="margin-bottom:0;">The
                Einstein Trust Layer dashboard is a dynamic dashboard. Because it’s a dynamic
                dashboard, it counts toward your total number of dynamic dashboards. See <a href="https://help.salesforce.com/s/articleView?id=analytics.dashboards_dynamic_overview.htm&amp;type=5&amp;language=en_US" target="_blank">Dynamic Dashboards</a>. </p>
            </td>

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

To see more details about toxicity in responses and data masking, use the pre-built Einstein Trust Layer Toxic Response reports.

 
| Report Name | What It Provides |
| --- | --- |
| Toxicity Detection in Responses | A detailed view of the toxic responses detected by the Einstein Trust Layer. Use it to see the response text and the number of toxicity detections by feature. |
| Masked Prompt and Response | A detailed view of the prompt with the masked data, the full prompt without the masking, and the response with and without the masked data. Use it to see what data was masked before sending it to the large language model (LLM). |

## Example: Get Insights with Queries

To analyze audit and feedback data, run queries on the applicable DMOs in the [Data Model for Generative AI Audit and Feedback](https://help.salesforce.com/s/articleView?id=ai.generative_ai_feedback_data_model.htm&release=264.0.0&type=5 "Understand and analyze your Einstein generative AI audit and feedback data by using the appropriate data model objects (DMOs). Einstein generative AI Audit and Feedback data is streamed to a data lake object (DLO) in Data 360 and mapped to data model objects (DMOs)."). See [Query Data in Data 360](https://help.salesforce.com/s/articleView?id=data.c360_a_query_data_in_dc.htm&type=5&language=en_US).

This query example shows linking GenAIGtwyObjRecord to an sObject to GenAIGatewayRequest or GenAIFeedback.

```
SELECT *
FROM "std__GenAiGatewayReqObjRecDmo__dlm"
JOIN "std__GenAiFeedbackDmo__dlm" ON "std__GenAiGatewayReqObjRecDmo__dlm"."std__AiFeedbackId__c" = "std__GenAiFeedbackDmo__dlm"."std__Id__c"
JOIN "std__GenAiResponseGenerationDmo__dlm" ON "std__GenAiFeedbackDmo__dlm"."std__RelatedAiResponseGenerationId__c" = "std__GenAiResponseGenerationDmo__dlm"."std__Id__c"
JOIN "std__GenAiGatewayResponseDmo__dlm" ON "std__GenAiResponseGenerationDmo__dlm"."std__AiGatewayResponseId__c" = "std__GenAiGatewayResponseDmo__dlm"."std__Id__c"
JOIN "std__GenAiGatewayRequestDmo__dlm" ON "std__GenAiGatewayResponseDmo__dlm"."std__AiGatewayRequestId__c" = "std__GenAiGatewayRequestDmo__dlm"."std__Id__c"
LIMIT 10
```

Suppose the sObject is Case.

- The query can get the number of generative AI requests used or called for the case.
- You can compare the time to resolve for cases with generative AI usage versus cases without generative AI usage.
- You can also link the GenAIFeedback table to determine whether generative AI was helpful, or just to give feedback to the generative AI for that particular case.

For more focused output, use table aliases and select a few specific columns to avoid duplicate column names.

```
SELECT req."std__PromptText__c", gen."std__GeneratedResponseText__c", fb."std__FeedbackTypeId__c", obj."std__RecordId__c"
FROM "std__GenAiGatewayReqObjRecDmo__dlm" obj
JOIN "std__GenAiFeedbackDmo__dlm" fb ON obj."std__AiFeedbackId__c" = fb."std__Id__c"
JOIN "std__GenAiResponseGenerationDmo__dlm" gen ON fb."std__RelatedAiResponseGenerationId__c" = gen."std__Id__c"
JOIN "std__GenAiGatewayResponseDmo__dlm" resp ON gen."std__AiGatewayResponseId__c" = resp."std__Id__c"
JOIN "std__GenAiGatewayRequestDmo__dlm" req ON resp."std__AiGatewayRequestId__c" = req."std__Id__c"
LIMIT 10
```

## Build Data 360 Reports

To analyze audit and feedback data, build reports in Data 360 that pull relevant information from the data model objects (DMOs) in the [Audit and Feedback data model](https://help.salesforce.com/s/articleView?id=ai.generative_ai_feedback_data_model.htm&release=264.0.0&type=5 "Understand and analyze your Einstein generative AI audit and feedback data by using the appropriate data model objects (DMOs). Einstein generative AI Audit and Feedback data is streamed to a data lake object (DLO) in Data 360 and mapped to data model objects (DMOs)."). You can use calculated insights to create metrics that can trigger alerts. To learn more, see [Data 360 Reports and Dashboards.](https://help.salesforce.com/s/articleView?id=data.datacloud_reports_dashboards_overview.htm&type=5&language=en_US)

## Tag Limits in the GenAIRequestTag Data Lake Object (DLO)

If you query GenAIRequestTag data in Data 360 for analytics, auditing, or debugging, Salesforce enforces a maximum number (default of 20) of individual rows written per LLM request. Tags that exceed that limit appear in a single `REMAINDER_TAGS` row containing a JSON array.

Reserved Planner Tags

Ten reserved planner tags are always individual rows. These tags don’t count toward the 20-tag limit.

- `action_id`
- `action_name`
- `bot_id`
- `bot_session_id`
- `bot_version_id`
- `plan_id`
- `planner_id`
- `user_context`
- `user_id`
- `x-client-trace-id`

Example `REMAINDER_TAGS` Entry

Here’s an example that shows the content of the `tagValue__c` field associated with the `REMAINDER_TAGS` entry in a single row.

```
[
        {
        "tagValue": "val_21_overflow",
        "tag": "np_21"
        },
        {
        "tagValue": "val_22_overflow",
        "tag": "np_22"
        },
        {
        "tagValue": "val_23_overflow",
        "tag": "np_23"
        },
        {
        "tagValue": "val_24_overflow",
        "tag": "np_24"
        },
        {
        "tagValue": "tag_test_org",
        "tag": "x-client-trace-id"
        }
]
```

Sample Data 360 SQL Query to Parse Tags, Including Remainder Tags

```
SELECT "std__TagText__c", "std__TagValueText__c", "std__CreatedDate__c"
FROM "std__GenAiGatewayRequestTagDmo__dlm"
WHERE "std__CreatedDate__c" >= TIMESTAMP '2026-03-27 04:00:00+00:00'
AND "std__TagText__c" = 'REMAINDER_TAGS'
ORDER BY "std__CreatedDate__c" DESC
LIMIT 10
```

Update Previous SQL Queries to Parse Remainder Tags

Previously-created SQL queries that filter by `tag__c` don't use overflow tags as individual rows. Update these queries to parse the `REMAINDER_TAGS` JSON value. Any dashboards, reports, or Data Cloud recipes that assume the one-row-per-tag approach can return incomplete results rather than errors.