AI engineering glossary · Prompt context engineering
What is context compression?
Context compression: Shrinking the material placed in a prompt, through summarising, removing low-value passages or dropping filler words, while keeping the facts needed for the task. It saves cost and delay and can improve focus on long inputs.
Context compression: an example
A 12,000-token set of meeting notes is reduced to a 2,500-token digest of decisions and action items.
Related terms
More Prompt context engineering terms
- Context engineering
- Context stuffing
- Context truncation
- Contrastive chain-of-thought
- Conversation buffer memory
- Conversation history
- Delimiters
- Developer message
Where you learn it
Context compression is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.