🎯
Context Engineering
The art of optimizing what goes into an LLM's context window — the single most important lever for agent quality.
3 patterns
Context Window Management
Intermediate
Strategically curate what goes into the LLM's context window to maximize output quality within token limits.
Structured Output
Basic
Constrain LLM outputs to follow a specific schema (JSON, XML, typed objects), ensuring reliable downstream processing.
Prompt Caching
Intermediate
Reuse previously processed prompt prefixes across API calls to reduce latency and cost.