Prompting & context · Glossary term
What is Context Compression?
Reducing the token footprint of source material while attempting to preserve the information required for a later model decision.
Why does Context Compression matter?
Compression can make long tasks fit within budget, but every omitted detail creates a risk that the model loses evidence, constraints, or unresolved state.
Context Compression in practice
Preserve authoritative facts and identifiers verbatim, summarize redundant history, attach source pointers, and test the compressed context on representative tasks.
What is the common confusion about Context Compression?
Compression is lossy unless it retains the full original. A shorter summary is not automatically an equivalent context.
Learn Context Compression in the course
Lessons that name Context Compression in a title or section
- Context Engineering: Windows, Budgets, Memory, and Retrieval
Prompt engineering is a subset. Context engineering is the whole game. A prompt is a string you type. Context is everything that goes into the model's window: system instructions, retrieved…
Covered in Phase 11: LLM Engineering.
Related terms
- Token BudgetAn explicit allocation of token capacity across instructions, evidence, history, tool results, reasoning or working space, and output.
- Context EngineeringDesigning the full information environment supplied to a model at each step, including instructions, selected files, retrieved evidence,…
- Progressive DisclosureSupplying a person or model with the minimum useful context first, then revealing deeper detail when the task or evidence requires it.
- HandoffA structured transfer of a task between people or agents that preserves the objective, current state, evidence, decisions, constraints,…
Sources
More terms in Prompting & context
This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.