A language model only knows what it was trained on and what you put in front of it. When your task depends on private documents, fresh facts, or a long conversation, the quality of the answer depends on what information the model can see when it responds.
You'll start with retrieval-augmented generation (RAG), where the system looks up relevant information and adds it to the prompt before the model answers. Then you'll move to context engineering, the wider skill of deciding what goes into the model's context, in what order, and what to leave out.
Once a model can work with the right information, you can let it take actions. That's the focus of Tools, Function Calling & Agents, the next module in this course.
A short introduction to RAG and how it lets a language model draw on a trusted source of information before it answers.
A plain-language look at RAG as an architecture pattern that combines the strengths of large language models with outside knowledge.
What context engineering is, how it differs from prompt engineering, and how it is used to build an AI agent.
Why prompt engineering is only the start, and how managing context helps agents actually work.