AI glossary
Context engineering
Context engineering is choosing what goes into a model's context on each call, instructions, history, documents and tool results, so it has what it needs and little else.
Prompt engineering is about the wording of one instruction. Context engineering is about everything around it, especially in an agent whose context fills up as it works.
Common moves are to summarise old turns, keep large tool results out of the context and store them aside, load files only when needed and give the model a short plan to come back to.
More context is not better context. Irrelevant text costs tokens and distracts the model, so the question each time is what this step really needs.
Learn it hands-on
These free lessons teach it with commands to run in a lab and checked tasks. Read them whole with no account.