Definition
What this term means
The maximum amount of text, measured in tokens, that an AI model can process in a single interaction. The context window determines how much information the model can consider when generating a response. Modern models like GPT-4o and Claude support context windows of 128,000+ tokens, but RAG-retrieved snippets are typically much shorter, making concise content crucial for citation.
Why it matters
The business impact
While context windows are growing larger, the practical implication for brand visibility is about efficiency: AI systems select and prioritise the most relevant content snippets within their context window. Pages that communicate key information clearly and concisely are more likely to be included in the model's working context, and therefore more likely to be cited in the response.
Used in context
How you might use this term
“A brand with 5,000-word product pages found their key differentiators were buried too deep to be reliably retrieved. By restructuring content to place critical information within the first 500 words and using clear heading hierarchies, their citation rate in AI responses improved significantly.”
Related terms
Explore connected concepts
Token
The fundamental unit of text that AI models process, roughly equivalent to three-quarters of a word in English. AI systems break all input text into tokens before processing it. Every word, punctuation mark, and space is tokenised. The number of tokens determines how much content fits within a model's context window and how much it costs to process.
LLM
A type of artificial intelligence model trained on vast datasets of text to understand, generate, and reason about human language. LLMs power the AI assistants and generative search tools, including ChatGPT, Google Gemini, Claude, and Perplexity, that are rapidly becoming the primary way people discover products, services, and information online.
RAG
An AI architecture that combines real-time information retrieval with language generation. Instead of relying solely on pre-trained knowledge, RAG systems search external sources, such as websites, databases, or knowledge bases, to find relevant information before composing their response. This is the technology behind AI search tools like Perplexity and Google's AI Overviews.