Module · Beginner
Teaching agents
How to give an agent knowledge it was never trained on: what RAG is, how to find, write and prepare documents, how to measure whether the agent sticks to them, and how to feed context that changes over time.
An agent is only as useful as what it knows about your business. This module shows how knowledge is collected, shaped, retrieved and verified.
- 1 Introduction to knowledge creation Understand which knowledge an agent needs, how it becomes usable evidence, and who keeps it trustworthy.
- 2 What is a RAG Learn how Retrieval-Augmented Generation finds relevant evidence before a model writes an answer, and why evidence still needs checking.
- 3 How to find and prepare knowledge Build an approved knowledge inventory by finding useful sources, prioritising real questions and resolving gaps before indexing.
- 4 How to write good documents Write knowledge documents that remain clear when searched in pieces, with explicit facts, conditions and useful examples.
- 5 Measuring adherence and hallucination Evaluate whether an agent's answers follow the evidence, cover the intended questions and acknowledge what the sources do not establish.
- 6 Retrieval strategies Choose search and ranking techniques that bring the right evidence into an agent's context without overwhelming it.
- 7 Preparing documents for knowledge Turn everyday files into clear, traceable knowledge that an agent can retrieve without losing important conditions.
- 8 Dynamic context Give an agent current, authorised facts about a conversation without confusing them with durable knowledge or permanent memory.