Prompt
Pronunciation: /prɒmpt/
The input text or instruction given to an AI model to guide its response.
Plain English Explanation
A prompt is what you type or provide to an AI model to tell it what you want. It can be a question, instruction, example, or combination of these. The quality of the prompt significantly affects the quality of the model's output.\n\nPrompt engineering — the skill of crafting effective prompts — has become a key discipline in working with AI systems.
Analogy
A prompt is like a brief you give to a contractor. The clearer and more detailed your brief, the more likely you are to get exactly what you wanted.
How is it used?
Every interaction with ChatGPT, Claude, or any LLM starts with a prompt. Developers embed prompts in applications to automate tasks like summarisation, classification, and content generation.
Real-world Example
Instead of prompting "Write about AI," a better prompt would be: "Write a 200-word explanation of machine learning for a 12-year-old, using an analogy about learning to ride a bicycle."
Common Misconceptions
More words in a prompt do not always mean better results. Effective prompts are clear and purposeful, not necessarily long.
History
Prompting as a concept existed in early language models, but the term "prompt engineering" gained prominence with GPT-3's in-context learning capabilities (2020).
Related Terms
See Also
Also known as: Prompt engineering input