Data Library setup considerations
Key Takeaway
A data library uses only one data source, and you can't change that source later. An agent can use a new library only after its build finishes and the status reads "Your data library is ready to use!".
An Agentforce Data Library connects agents and other AI features to your own content, such as Knowledge articles or uploaded files, so their answers are grounded in trusted data. When you save a library, Salesforce automatically builds the Data 360 pieces behind it: data streams, data objects, a search index and a retriever. Good setup means choosing the right data source, permissions and settings before you save, because you can't change some choices later.
What a data library does
An Agentforce Data Library improves the accuracy of AI features, such as Agentforce agents, by connecting them to trusted data sources. A library works with unstructured or semi-structured data, such as documents or large text fields, and turns that data into searchable information.
Each data library has its own retriever. Several retrievers can point to the same search index, but each pointer is unique.
When you connect a library to an agent, the Answer Questions with Knowledge action uses the library's search index and retriever to answer questions.