Foundations — prompt vs. context engineering, the attention budget, the "right altitude"

Context engineering is the successor concept to prompt engineering. Where prompt
engineering asks how do I phrase the request, context engineering asks what
should be in the model's working memory at all, including retrieved documents,
prior conversation, tool definitions, and long-term memory. The governing
constraint is the model's finite attention budget: there is a limited, high-value
space, and good context engineering means finding the smallest set of high-signal
tokens that make the desired outcome likely. Students also learn the "right
altitude" principle — prompts should be specific enough to steer behaviour but not
so brittle that they hardcode logic, and not so vague that they assume context the
model does not have.