Context Engineering

If you're writing system prompts or building agents, this is the reference for understanding what context actually is and how models process it. It breaks down the anatomy (system prompts, tool definitions, retrieved documents, message history, tool outputs) and explains why bigger context windows don't solve everything. The progressive disclosure principle alone is worth the read: load skill descriptions upfront, full content only when activated. Most useful when you're debugging why an agent is underperforming or trying to optimize token usage. Treats context as a finite attention budget rather than unlimited memory, which matches how these systems actually behave.