Use Agentforce Data Library to configure the Knowledge Action and enhance the accuracy of AI in your features.
Required Editions
| Available in: Lightning Experience |
| Available in: Enterprise, Performance, and Unlimited Editions with the Einstein for Platform or Einstein or Agentforce for Sales or Service add-on, or Agentforce Foundations |
| User Permissions Needed | |
|---|---|
| To set up Agentforce Data Libraries: | Data Cloud admin AND System Administrator permissions. |
To use Agentforce Data Libraries, you must have Data 360 set up. Data libraries consume Data 360 credits.
Important Web search isn't supported for new data libraries. To search the web in
your agents, use the Search the Web standard action. To search the web in
your prompt templates, use the web retriever in Prompt Builder.
You can create and assign data libraries to features from Agentforce Data Library setup or when you configure an agent in Agentforce Builder. Learn how to.
- Create a Data Library
Create a data library and give it a unique name. - Choose A Data Source for Your Library
When you configure a data library, you can add knowledge articles, uploaded files, or custom retrievers as a data source. The data source is indexed on Data Cloud where a search index and retriever are automatically created for you. When integrated with AI agents, the data library’s search index and retriever are used by the Answer Questions with Knowledge action. - Connecting Data Libraries to Agents
After you create a data library, assign it to your agent to ground responses with trusted data. - Test Data Libraries in a Sandbox
A sandbox is a copy of your Salesforce org that you can use for development, testing, and training without compromising the data and applications in your production org. Agentforce Data Library is supported in all the sandbox types: Developer, Developer Pro, Partial Copy, and Full Copy.