Metadata Studio

Use the Metadata Studio to enhance your generative AI results across Salesforce apps that are integrated with Data Prism, such as Einstein Segment Creation. With the Metadata Studio, review and validate all your objects and fields, add missing descriptions, and enhance AI-generated descriptions to gain an accurate semantic representation when querying natural language prompts. If needed, you can also exclude irrelevant objects in the data source so that they aren’t sent to the Large Language Models (LLMs) or returned when grounding.

Required Editions

Note Prism and Metadata Studio aren’t supported in Government Cloud Plus. Don’t turn on the feature in Government Cloud Plus orgs. Contact your Salesforce account executive for more details.

Available in: Lightning Experience

Available in: Enterprise, Performance, Unlimited, and Developer Editions with Foundations, or Agentforce 1 or Einstein 1 Editions

Data Prism pinpoints the exact data entities relevant to the natural language question, increasing the accuracy of results and providing greater coverage of data. For more information, see Einstein Data Prism.

The Metadata Studio is accessible from the App Launcher.

Metadata Studio Use Case

The Metadata Studio is used to review the accuracy of the metadata labels and descriptions, add missing descriptions, and exclude unnecessary entities.

Solar Panel Company A company that sells solar panels has created a custom object to track their attributes: SP_info_att. The object contains no description. When scanning the object, Data Prism auto-generates the description to "The table holds attributes of stored procedures," thinking that SP stands for Stored Procedures. With Metadata Studio, the user can update the labels and descriptions of the SP_info_att object and fields to something relating to Solar Panels. Now that the data has a more accurate semantic representation, Data Prism can return the custom object when a user asks a natural language question about solar panels.