DictionaryContext Management
Context Engineering
Choosing exactly what information to hand the AI, like packing only what you need for a trip.
Definition
The discipline of designing and managing the information provided to an AI model to maximize output quality while minimizing token costs. Encompasses prompt design, file selection, caching strategy, and context window management.
Example
Instead of attaching the whole repo, you give the agent the failing test, the function it calls, and the project's CLAUDE.md.
Appears in
- TRACE: TRajectory Attribution for Automated Context EngineeringarXiv
- Tokalator: A Context Engineering Toolkit for Artificial Intelligence Coding AssistantsarXiv
- The Root Theorem of Context EngineeringarXiv
- Meta Context Engineering via Agentic Skill EvolutionarXiv
- CEDAR: Context Engineering for Agentic Data SciencearXiv
- Monadic Context EngineeringarXiv