Prompt Engineering
Also known as: Prompt Design, Prompt Crafting, In-Context Learning
The practice of designing, optimizing, and structuring inputs (prompts) to AI language models to elicit desired outputs, including techniques for instruction formatting, context provision, and output specification.
Sources & References
DAIR.AI
Related Terms
Chain-of-Thought
A prompting technique that improves AI reasoning by instructing the model to decompose complex problems into intermediate reasoning steps before arriving at a final answer.
Context Window
The maximum amount of text (measured in tokens) that a large language model can process in a single interaction, encompassing both the input prompt and the generated output. Managing context windows effectively is critical for enterprise AI deployments where complex queries require extensive background information.
Few-Shot Learning
A machine learning approach where models learn to perform tasks from only a small number of examples, typically provided within the prompt or during a brief adaptation phase.
Large Language Model
A type of AI model trained on vast amounts of text data that can understand, generate, and manipulate human language, typically based on the transformer architecture with billions of parameters.
Tokens
The basic units of text that language models process, typically representing words, subwords, or characters. Token counts determine context window usage and API costs.