Daniel & Friends / Glossary / Context window
AI and automationContext window
The context window is the amount of text a model can process at once, including the instruction and the answer. What does not fit in the window, the model does not see.
Daniel Votruba ·
In practice
Put only what the task needs into the window. A long and messy context makes answers worse and raises the cost.
Related terms
- Token: A token is the unit of text a language model works with: usually a fragment of a word or a short word.
- Large language model (LLM): A large language model is a model trained on a huge amount of text that predicts the next words and can write, summarise and answer.
- RAG (retrieval-augmented generation): RAG is a method in which a model first retrieves relevant documents, for example company knowledge, and answers from them.
- Prompt: A prompt is the instruction a model receives.
More terms in the group AI and automation
Copilot (AI assistant) · Computer vision · Custom GPTs and projects · ChatGPT Ads · Deepfake and synthetic media · Chain of thought · Deep learning · C2PA and content provenance (AI watermarks) · Diffusion models · Automation platforms (Zapier, Make, n8n) · Embedding · AI workflow and orchestration · EU AI Act · AI slop · Explainable AI (XAI) · AI search (answer engines) · Few-shot and zero-shot prompting · AI SDR · Fine-tuning · AI scoring · Foundation model · AI safety and alignment · Function calling (tool use) · AI personalization
Terms in practice
Need help putting them to work?
Terms are one thing, putting them to work is another. We go through which of them pay off for you and say so plainly. You get a first opinion for free and we reply within 24 hours.
Book a call