Giving a model a set of documents to search at the moment it answers, so the reply is drawn from that material rather than from its training alone. It is the mechanism behind a knowledge base, and it is taught under that name on the AI Agents in Action day.
It is taught as a mechanism rather than as theory, in the session on knowledge bases, and the distinction that matters in practice is the one drawn elsewhere in the catalogue: an agent with a live database it can read and write has memory where an agent with a fixed knowledge base does not.
The outcome this is usually the way of achieving.
Read GroundingThe systems that use a knowledge base this way.
Read AI agentThe day that covers knowledge bases and RAG together.
Read AI Agents in Action: Practical Use with Microsoft CopilotEvery term used across this site's training courses, its audit methodology and the two regulations behind them, in one place.
Back to the glossary