From tokens to agents, the AI dictionary.
LLM, RAG, MCP, embedding, fine-tuning… The most-used concepts of modern AI — plain language, real-world examples, and clean illustrations.
Featured terms
The most searched, most misunderstood concepts in modern AI.
Artificial Intelligence
The broad field of building machines that mimic human-like learning, reasoning, and decision-making.
Machine Learning
Letting computers learn patterns from data instead of being explicitly programmed.
LLM
A massive AI model trained on huge text corpora that learns to predict the next token and can hold conversations.
Transformer
The neural-network architecture behind modern LLMs that learns how much each word should attend to every other word.
Embedding
A vector representation that captures the meaning of a piece of text, image, or audio.
RAG
Query → document retrieval → LLM context injection → answer generation.
MCP
An open protocol that lets AI applications connect to external data sources and tools in a standardized way.
AI Agent
An autonomous system that uses an LLM as its brain to call tools, plan, and reach a goal step by step.
Prompt
The input text you give an LLM — its quality largely determines the quality of the answer.
Calculators & tools
From token cost to GPU sizing — practical answers to the questions you face when shipping AI.