AI Glossary
Every AI term explained simply. From LLMs to RAG to agentic AI.
Agentic AI
Agentic AI refers to AI systems designed to operate with significant autonomy, making decisions, executing multi-step plans, and adapting to achieve goals with minimal human oversight.
AI Agent
An AI agent is an autonomous system that uses a language model to reason, plan, and take actions through tools and APIs to accomplish goals with minimal human intervention.
Attention Mechanism
The attention mechanism is a neural network component that allows models to focus on the most relevant parts of the input when producing each element of the output.
Chain-of-Thought (CoT)
Chain-of-thought is a prompting technique that improves AI reasoning by asking the model to show its step-by-step thinking process before arriving at a final answer.
Computer Vision
Computer vision is the field of AI that enables machines to interpret and understand visual information from images, videos, and the real world.
Context Window
The context window is the maximum amount of text (measured in tokens) that an AI model can process in a single interaction, including both the input and the output.
Diffusion Model
A diffusion model is a type of generative AI that creates images by gradually removing noise from a random pattern, guided by text descriptions or other conditioning inputs.
Embedding
An embedding is a numerical vector representation of text, images, or other data that captures semantic meaning, allowing AI systems to measure similarity between concepts.
Few-Shot Learning
Few-shot learning is the ability of AI models to perform a task after being shown only a small number of examples, without requiring fine-tuning or retraining.
Fine-Tuning
Fine-tuning is the process of further training a pre-trained AI model on a specific dataset to specialize it for a particular task or domain.
Function Calling
Function calling is an AI model capability that allows it to generate structured requests to external functions or APIs based on natural language conversation.
Generative AI
Generative AI refers to AI systems that can create new content including text, images, audio, video, and code based on patterns learned from training data.
Hallucination
A hallucination occurs when an AI model generates confident-sounding information that is factually incorrect, fabricated, or not supported by its training data.
Large Language Model (LLM)
A large language model is a type of AI trained on massive text datasets that can understand and generate human-like text.
Model Context Protocol (MCP)
The Model Context Protocol is an open standard that provides a universal way for AI models to connect with external data sources, tools, and services through a standardized interface.
Multimodal AI
Multimodal AI refers to models that can process and generate multiple types of data including text, images, audio, and video within a single system.
Natural Language Processing (NLP)
Natural language processing is the field of AI focused on enabling computers to understand, interpret, generate, and interact with human language.
Neural Network
A neural network is a computing system inspired by the human brain, consisting of interconnected layers of nodes that learn patterns from data.
Prompt Engineering
Prompt engineering is the practice of crafting effective inputs to AI models to produce desired outputs, including techniques like few-shot examples, chain-of-thought reasoning, and system prompts.
Reasoning Model
A reasoning model is an AI system specifically optimized for complex multi-step thinking, logical deduction, and problem-solving through extended internal deliberation.
Reinforcement Learning (RL)
Reinforcement learning is a machine learning paradigm where an AI agent learns to make decisions by receiving rewards or penalties for its actions in an environment.
Retrieval-Augmented Generation (RAG)
RAG is a technique that enhances AI model responses by retrieving relevant information from external knowledge sources before generating an answer.
System Prompt
A system prompt is a set of instructions given to an AI model that defines its behavior, personality, capabilities, and constraints for the entire conversation.
Temperature
Temperature is a parameter that controls the randomness and creativity of AI model outputs, with lower values producing more focused responses and higher values producing more diverse ones.
Tokens
Tokens are the basic units of text that AI language models process, typically representing words, parts of words, or individual characters.
Tool Use
Tool use is the ability of AI models to interact with external tools, APIs, and services to accomplish tasks beyond text generation.
Top-p (Nucleus Sampling)
Top-p is a text generation parameter that limits the model's token selection to the smallest set of tokens whose cumulative probability exceeds a threshold p.
Transformer
A transformer is a neural network architecture that uses self-attention mechanisms to process sequential data, forming the basis of all modern large language models.
Vector Database
A vector database is a specialized database designed to store, index, and query high-dimensional vector embeddings for fast similarity search.
Zero-Shot Learning
Zero-shot learning is the ability of an AI model to perform a task it has never been explicitly trained on, using only natural language instructions without any examples.