The Essential AI Tech Glossary

A type of artificial intelligence trained on vast amounts of text data to understand and generate human-like language. Examples include GPT-4, Claude 3.5, and Gemini.

A technique that enhances LLM responses by fetching relevant information from external data sources (like your own documents) before generating a final answer, reducing hallucinations and providing up-to-date context.

An open standard that enables AI models to safely and easily connect to local or remote data sources and tools, standardizing how AI "agents" interact with the world.

A specialized database that stores data as mathematical vectors (embeddings), allowing AI systems to perform "semantic search" to find related information based on meaning rather than just keywords.

A system where an AI agent can plan multi-step tasks, use tools, and verify its own work autonomously rather than just providing a single response to a prompt.

When an AI model generates information that sounds confident and plausible but is factually incorrect or disconnected from its training data.

The maximum amount of information (measured in tokens) an AI model can "keep in mind" at one time during a conversation.

The process of taking a pre-trained AI model and training it further on a smaller, specific dataset to adapt it for a particular task or domain.

Mathematical representations of data (text, images, etc.) in a high-dimensional space where similar meanings are placed closer together.

The practice of designing and refining inputs (prompts) to get the most accurate or creative results from an AI model.

Asking an AI model to perform a task without giving it any examples of how to do it.

Providing an AI model with a few examples of a task within the prompt to help it understand the desired output format or logic.