Glossary
Context Window
A context window is the amount of text and other tokens a language model can consider in one interaction, including instructions, conversation history and retrieved documents. Material outside the active window cannot directly influence that response, even if it appeared earlier in a long session.
In plain terms
It is the model’s working space for the current answer.
Why it matters
Retrieved passages compete for limited attention, so concise, self-contained evidence is easier to use than sprawling or repetitive copy.
How to apply it
- Put the answer and evidence close together.
- Make sections understandable without earlier page context.
- Avoid repeating low-value boilerplate around key facts.
Example
A long report is retrieved as a few relevant passages because the entire document and all other sources cannot fit into the answer context.
Sources
Related reading
Related terms
Back to the full glossary (75 terms).
Ranking is no longer enough
You need to be cited, mentioned, and recommended.
Being cited, mentioned, and recommended are three different outcomes, and most brands only ever achieve the first one. Ranking is no longer enough because AI engines answer buyers directly and name only a short list of vendors as the recommendation — everyone else is cited in passing, if at all. Get a free AI Visibility Report to see exactly where your brand appears today across ChatGPT, Google AI Overviews, Gemini, Perplexity, and Copilot, where competitors are winning the recommendation instead, and what's keeping you from moving up the shortlist.