· intermediate
Context Engineering
Deciding what a model sees is a bigger lever than deciding how you ask. Budgets, retrieval, ordering and compaction, and how to tell whether your pipeline is helping.
Written in house, from the work rather than from a syllabus. Every example is one we would use ourselves, and every quiz question explains why its answer is right.
What you’ll learn
- Treat the context window as a budget with competing claims
- Decide what deserves space and what does not
- Account for position effects when ordering material
- Compact history without losing what mattered
- Recognise that tool definitions are context too
- Evaluate a retrieval pipeline rather than trusting it
Before you start
- · Generative AI Foundations and Prompt Engineering
- · No coding required, though examples assume you are building something