Agents can be connected to external knowledge sources through Retrieval-Augmented Generation (RAG).
This is a technique where a language model first retrieves relevant information from external data sources and then uses that information to generate more accurate, up-to-date and context-aware responses.
These external sources are often:
This is ideal for Agents designed to help with:
The Knowledge Base is the memory of the Agent.
Within the Agent Workspace you can easily manage your Knowledge Base. You can find a more detailed explanation here.