Context Engineering
The practice of shaping and managing information fed to an AI model for optimal results.
The quality of AI output is directly proportional to the quality of its input. Context engineering is the difference between an agent that gives generic answers and one that understands your specific business.
Our CLAUDE.md file is context engineering in action: it tells Claude Code our architecture (n8n-first), conventions (TypeScript strict, fi+en), and constraints (ISO 27001) so every output aligns with our system.
Related terms
Context Window
The AI model's "working memory" — how much information it can process at once (e.g., 1 million tokens for Claude Opus 4.6).
Prompt
An instruction or question given to an AI model. Quality determines output quality.
Context Rot
Degradation of model accuracy as the context window fills with too much information.
Memory (Agent)
Mechanisms that allow an agent to retain and recall information across sessions.