To improve your Einstein results in Data Prism integrated apps, validate an object or field label, by adding or editing an entity description. Standard objects and fields with a description are automatically imported from Salesforce documentation and they’re marked as validated. You can still edit them if you have additional information that’s relevant.
Required Editions
| Available in: Lightning Experience |
| Available in: Enterprise, Performance, Unlimited, and Developer Editions with Foundations, or Agentforce 1 or Einstein 1 Editions |
| User Permissions Needed | |
|---|---|
| To review metadata: |
Metadata Studio User OR Modify All Data |
Custom objects and field descriptions are automatically imported or generated using sample data and Large Language Models (LLMs) via the Salesforce LLM gateway, which uses Salesforce’s trust layer including PII detection. For more information about PII masking, see Data Masking.
You can focus on specific metadata by selecting a data source or relevant dataspace depending on your purchased products. If you have Data Cloud all available dataspaces appear.
To validate metadata entities:
- From the App Launcher, select Metadata Studio
- Select the required data source (if you have Data Cloud, all relevant dataspaces appear. If you have a Core App, the Core org appears.). You can only select one data source at a time, but you can validate the metadata for all your data sources if necessary. If a description is missing during the scan process, an automatically generated description appears in the Metadata Studio (All generated descriptions appear in light blue, indicating they were generated by generative AI).
- Review the generated description, and edit it if more information is needed.
- To validate, select the dropdown and then select Validate.
- If you want to validate more than one entity, select all the entities you’re validating and then on the top right, click Validate.