Loading
Upcoming Mandatory Changes to Public Key Infrastructure (PKI)Read More
Salesforce Enforces New Security Requirements in Summer 2026Read More
Agentforce and Einstein Generative AI
Table of Contents
Filter by (0)Add
Select Filters

          No results
          No results
          Here are some search tips

          Check the spelling of your keywords.
          Use more general search terms.
          Select fewer filters to broaden your search.

            Search all of Salesforce Help
            Search all of Salesforce Help
            Create Data Streams to Monitor Einstein Service Replies

            You are here:

            1. Salesforce Help
            2. Docs
            3. Quickstart Your Einstein Generative AI Solution

            Create Data Streams to Monitor Einstein Service Replies

            Create data streams to bring the case and message data stored in Salesforce CRM objects into Data 360.

            Required Editions

            Available in: Enterprise, Performance, and Unlimited 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.
            User Permissions Needed
            To edit a data stream Customer Data Cloud Admin or Customer Data Cloud for Marketing Data Aware Specialist
            To turn on data collection: View Setup
              AND
              Customize Application

            To collect generative AI audit and feedback data, Set Up Einstein Generative AI Audit and Feedback.

            Creating data streams to bring the case and message data into Data 360 is one of the steps required to create reports so you can analyze and monitor Einstein Service Replies. See Monitor and Analyze Einstein Service Replies.

            1. In Data Cloud, go to the Data Streams tab and click New.
            2. For the data source, select Salesforce CRM and click Next
            3. Select a Salesforce org. If you have only one Salesforce org connected to Data Cloud, it’s selected by default.
            4. Select All Objects and click Next.
            5. Select Case and click Next.
            6. Select the fields that you want to include, and click Next. Make sure to select Id, System Modstamp.
            7. For Category, select Engagement.
            8. For Event Time Field, select System Modstamp and click Next.
            9. Name the data stream Case Information, select the data space, and click Deploy.
            10. On the data stream page, click Start in the data mapping section.
            11. Click Select Object and select Custom Data Model.
            12. Click New Custom Object and click Save.
            13. Repeat these steps for the Messaging Session or the Live Chat Transcript object. If you use both Messeging for In-app and Salesforce Chat, repeat the steps for both objects.

            You now map the fields in the data stream to create a custom data model. See Link Case and Messaging DMOs to Generative AI Data .

             
            Loading
            Salesforce Help | Article