Context Engineering

Auto-generated from data/terms.json. Do not edit this file manually.

Context Window

The context window is the amount of information a language model can consider at once when generating a response. It acts as the model's working memory, including both the input provided and the output it has generated so far. A larger context window allows the model to handle longer prompts, maintain coherence over extended interactions, and work with more complex information, while a smaller context window limits how much the model can reference at one time.

Also known as: token window

Sources:

• https://www.coursera.org/articles/context-window
• https://docs.claude.com/en/docs/build-with-claude/context-windows/

Prompt

A prompt is the input or instruction given to an AI system to guide its output. It provides context, goals, constraints or examples that influence how the model responds. Prompts are written in natural language (and sometimes combined with structured elements), and the clarity and structure of the prompt directly affect the quality of the AI's response.

Also known as: prompting, prompt engineering, prompting techniques

Sources:

• https://dictionary.cambridge.org/dictionary/english/prompt
• https://www.ulethbridge.ca/teachingcentre/what-are-prompts