📖 AI Glossary

Understand AI terms in plain English

A

AI Agent

An AI system that can autonomously perform tasks, make decisions, and interact with other systems to achieve goals. Unlike simple chatbots, agents can take actions.

Example: An AI agent that schedules meetings by checking your calendar, sending invites, and finding optimal times.

API (Application Programming Interface)

A way for software applications to communicate with each other. AI APIs let developers integrate AI capabilities into their apps.

C

Chatbot

An AI program designed to simulate conversation with human users, typically through text. Examples include ChatGPT, Claude, and customer service bots.

Context Window

The amount of text an AI can "remember" in a conversation. Larger context windows (like Claude's 200K tokens) mean the AI can work with longer documents.

G

Generative AI

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

Examples: ChatGPT (text), Midjourney (images), ElevenLabs (voice)

GPT (Generative Pre-trained Transformer)

The architecture behind ChatGPT. A type of large language model trained to predict and generate human-like text.

L

LLM (Large Language Model)

AI systems trained on vast amounts of text data to understand and generate human language. Examples include GPT-4, Claude, and Gemini.

M

Machine Learning (ML)

A subset of AI where computers learn patterns from data without being explicitly programmed for every scenario.

Multimodal AI

AI systems that can understand and work with multiple types of input — text, images, audio, and video — simultaneously.

N

Neural Network

Computing systems inspired by biological brains, composed of interconnected nodes (neurons) that process information in layers.

P

Prompt

The input or instruction you give to an AI to get a response. Better prompts lead to better outputs.

Prompt Engineering

The art of crafting effective prompts to get better results from AI. Includes techniques like chain-of-thought, few-shot learning, and role prompting.

R

RAG (Retrieval-Augmented Generation)

A technique where AI retrieves information from a knowledge base before generating responses, making answers more accurate and current.

T

Token

Units of text that AI models process. Roughly 1 token = 4 characters or 0.75 words. Context windows and pricing are often measured in tokens.

Transformer

The neural network architecture behind modern LLMs. Enables AI to understand relationships between words across long distances in text.