That is not a disclaimer — it is part of the point. The slides and the voice narrating the lectures were produced with AI tools, but every script was written and fact-checked by a human instructor with real hands-on experience. Think of the AI as the production crew; the teaching is human. Two teams, the same model, the same task. One ships something magical. The other ships something that hallucinates, forgets, and falls apart. The difference is almost never the model. It’s what they put in front of it — the context. This course is how you take control of that.
What you will learn:
Context Engineering is the discipline of deciding what goes into a model’s window — in what form, in what order, within a finite budget. You’ll understand the seven ingredients every context is made of — system prompt, instructions, examples, retrieval, memory, tools, and input. The failure modes that silently wreck quality — lost in the middle, context rot, poisoning. And how to manage it all at scale with compaction, memory, and measurement.
What this course covers, module by module:
What Is Context Engineering?; The Context Window; Anatomy of a Context; System Prompt & Instructions; Examples & Few-Shot; Retrieval as Context; Memory as Context; Tools as Context; Context Failure Modes; Compaction & Summarisation; Ordering & Structure; Measuring & Optimising; Context in Agents.
