Context Engineering

Context engineering is the discipline of carefully constructing, compressing, and managing the information fed into an LLM's context window to maximise the quality of its outputs. It's more than prompt engineering — it includes retrieval strategies (what to pull from memory or search), context ordering (what goes first matters), token budgeting (fitting the most signal into limited space), and dynamic context assembly (building different context payloads for different tasks). As agents tackle more complex tasks, context engineering becomes the primary lever for agent quality.