AI Glossary

Artificial Intelligence (AI)

The simulation of human intelligence processes by machines, especially computer systems, including learning, reasoning, and self-correction.

AI Agent

An autonomous AI system that can perceive its environment, make decisions, and take actions to achieve specific goals without constant human input.

API (Application Programming Interface)

A set of rules and protocols that allows different software applications to communicate with each other. AI APIs let developers integrate AI capabilities into their own apps.

Automation

The use of software to perform tasks with minimal human intervention. AI automation uses machine learning to handle complex, variable workflows.

Benchmark

A standardized test used to measure and compare the performance of AI models on specific tasks such as reasoning, coding, or language understanding.

Context Window

The maximum amount of text (measured in tokens) that an AI model can process at once. Larger context windows allow longer conversations and documents.

Chain of Thought (CoT)

A prompting technique that encourages AI models to show their reasoning step-by-step before giving a final answer, improving accuracy on complex problems.

Diffusion Model

A type of generative AI model that creates images by learning to reverse a process of adding noise. Used by tools like Stable Diffusion and DALL-E.

Embedding

A numerical representation of text, images, or other data as a vector of numbers. Embeddings allow AI to understand semantic similarity between concepts.

Fine-Tuning

The process of further training a pre-trained AI model on a specific dataset to specialize it for a particular task or domain.

Foundation Model

A large AI model trained on broad data that can be adapted to many downstream tasks. Examples include GPT-4, Claude, and Gemini.

Generative AI

AI systems that can create new content — text, images, audio, video, or code — rather than just classifying or predicting from existing data.

Hallucination

When an AI model generates information that sounds plausible but is factually incorrect or completely fabricated. A key challenge in deploying LLMs.

Large Language Model (LLM)

A type of AI model trained on massive amounts of text data to understand and generate human language. Examples: GPT-4, Claude 3, Llama 3.

Multimodal AI

AI systems that can process and generate multiple types of data — such as text, images, audio, and video — within a single model.

Prompt

The input or instruction given to an AI model to guide its output. Crafting effective prompts (prompt engineering) is key to getting good results.

RAG (Retrieval-Augmented Generation)

A technique that enhances LLM responses by retrieving relevant documents from a knowledge base and including them in the context before generating an answer.

Token

The basic unit of text that AI models process. A token is roughly 4 characters or 0.75 words. Model pricing and context limits are measured in tokens.

Transformer

The neural network architecture that underpins most modern LLMs. Introduced in the 2017 paper "Attention Is All You Need" by Google researchers.

Vector Database

A database optimized for storing and searching embeddings (vector representations). Used in RAG systems to find semantically similar content quickly.