Prompt
A prompt is the text you give a language model to tell it what to produce, including the task, any background it needs, and the rules the output must follow.
A prompt is not just a question. In practice it carries several distinct jobs: naming the role the model should adopt, supplying context the model cannot infer, stating the task, bounding the output with constraints, and defining the format. Prompts that separate these explicitly behave more predictably than prompts that mix them into one paragraph.
Related terms
- Prompt engineering
- Prompt engineering is the practice of writing and refining model instructions so that a language model produces the output you want reliably, rather than occasionally.
- System prompt
- A system prompt is a persistent instruction that sets a model’s role, rules, and boundaries for an entire conversation, separate from the individual messages a user sends.
- Context window
- A context window is the maximum amount of text, measured in tokens, that a model can consider at once — including the prompt, any supplied documents, and the reply it generates.
More on core concepts
See the full glossary, read the guides, or put it into practice in the prompt builder.