Glossary · 1 · Foundations: how AI works
Context window
Also known as: Context length
The context window is the maximum amount of text, measured in tokens, that a language model can take into account at once — the prompt, any attached documents, the conversation so far and its own answer. Anything outside the window is invisible to the model.
- Beginner
- Technical writers
- Technical project managers
- Developers
In one sentence
Context window defined: how much text an LLM can consider at once, why long chats lose details, and how it shapes RAG design.
Example
A 400-page manual may not fit into a model’s context window; a retrieval system instead selects the five most relevant sections and passes only those.
Why it matters on your learning path
- Technical writers: A big context window doesn’t mean the model uses everything equally well. Focused, relevant excerpts give better answers than whole manuals.
- Technical project managers: Context size affects cost and latency. Bigger isn’t automatically better for a use case.
- Developers: Manage the window deliberately: trim history, summarize, retrieve — see context engineering.