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
            Set Up Knowledge/RAG Quality Data and Metrics

            You are here:

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

            Set Up Knowledge/RAG Quality Data and Metrics

            Turn on Knowledge/RAG Quality Data and Metrics to collect and store, in Data 360, quality scores and other data about knowledge retrievals.

            Required Editions

            Available in: Lightning Experience
            Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type.
            User Permissions Needed
            To turn on data collection: View Setup
              AND
              Customize Application

            Setup considerations:

            1. Confirm that Data Cloud is provisioned in your Salesforce org and that you’ve turned on Einstein. To learn more, see Set Up Einstein Generative AI.
            2. Verify that you have the latest version of the Salesforce Standard Data Model (version 1.130 or higher) in your org (sandbox or production). From Setup, go to Apps -> Packaging -> Installed Packages -> Salesforce Standard Data Model. To get the required version, click here and follow the instructions.
            3. From Setup, in the Quick Find box, enter Einstein Audit, Analytics, and Monitoring Setup, and then select Einstein Audit, Analytics, and Monitoring Setup.
            4. Confirm that Audit and Feedback is turned on. To learn more, see Set Up Einstein Generative AI Audit and Feedback.
            5. Scroll down to Knowledge/RAG Quality Data and Metrics.
              Toggle for Knowledge/RAG Quality Data and Metrics in Setup
            6. Turn Knowledge/RAG Quality Data and Metrics on or off.
              1. Turn on Knowledge/RAG Quality Data and Metrics to provision your data model (in just a few minutes) and start collecting data in Data 360. Data collection occurs every five minutes, data processing occurs every hour, and data reporting is aggregated daily.
                Turning on Knowledge/RAG Quality Data and Metrics increases your org’s Flex credit consumption rate for LLM calls (see Flex Credits Billable Usage Types).
              2. Turn off Knowledge/RAG Quality Data and Metrics to stop collecting data.
                Suspending data collection keeps your existing data so that you can resume later. Dashboards, queries, and reports show a gap during which data collection is turned off.
            7. If prompted (for example, if you turn on data collection on and your org has multiple data spaces), select a target data space to store the data.
            8. Optionally, adjust the sampling rate, which is the percentage of retrievals you want to score and analyze. The default sample rate is 50%.
              An LLM scores retrieval quality, which consumes Flex credits. As RAG quality scores stabilize over time, consider lowering the sample rate to reduce the number of LLM calls and Flex credit consumption.
            9. To protect access to collected data that is sensitive, apply permissions at the dataspace level. That way, only authorized users can view or query this data. See Implement Data Governance Permissions for Agentforce Session Tracing Objects.
             
            Loading
            Salesforce Help | Article