Action Model
An internal model used by AI agents to predict the potential outcomes of their actions in specific states.
Category: Core Concepts
Read more →AI Agent Glossary
A comprehensive guide to AI terminology and concepts. Explore 62 essential terms to enhance your understanding of artificial intelligence.
A
11 terms
Agent
An AI system capable of taking actions autonomously to achieve specific goals in an environment.
Category: Core Concepts
Read more →Agent Architecture
The organizational structure and interaction patterns of internal components within an AI agent, such as perception, decision-making, and action modules.
Category: System Architecture
Read more →Algorithm
A set of rules or instructions designed to solve a specific problem or perform a task.
Category: Core Concepts
Read more →Artificial General Intelligence (AGI)
A hypothetical type of AI that matches or exceeds human cognitive abilities across all domains.
Category: Advanced Concepts
Read more →Artificial General Intelligence (AGI)
A hypothetical form of AI that matches or surpasses human intelligence across virtually every domain.
Category: Advanced Concepts
Read more →Artificial Intelligence (AI)
The simulation of human intelligence in machines programmed to think and learn like humans.
Category: Core Concepts
Read more →Artificial Superintelligence (ASI)
AI that is much more intelligent than the best human minds in virtually every domain.
Category: Advanced Concepts
Read more →Artificial Superintelligence (ASI)
AI that exceeds the capabilities of the best human minds in nearly every field.
Category: Advanced Concepts
Read more →Autonomous Agent
An AI system that operates independently without human intervention to achieve specific objectives.
Category: Agent Types
Read more →Autoregressive Model
A type of model that predicts the next element in a sequence based on previous elements.
Category: Core Technologies
Read more →B
2 terms
BERT
Bidirectional Encoder Representations from Transformers - a pre-trained language model.
Category: Core Technologies
Read more →Bot
An automated software application designed to perform specific tasks or simulate conversations.
Category: Agent Types
Read more →C
5 terms
Chatbot
An AI system designed to simulate conversation with human users through text or voice.
Category: Agent Types
Read more →Cognitive Computing
AI systems that simulate human thought processes, emphasizing learning, reasoning, and natural interaction.
Category: Advanced Concepts
Read more →Computer Vision
AI technology that enables machines to interpret and understand visual information from images and videos.
Category: Technical Capabilities
Read more →Context Window
The maximum amount of text that an AI model can process and remember in a single interaction.
Category: Technical Capabilities
Read more →Conversational AI
Technology that enables computers to interact with humans through natural language (speech or text).
Category: Applications
Read more →D
1 term
Deep Learning
A subset of machine learning using neural networks with multiple layers to learn complex patterns.
Category: Core Technologies
Read more →E
2 terms
Embedding
A numerical representation of data that captures semantic meaning in a high-dimensional vector space.
Category: Core Technologies
Read more →Explainable AI (XAI)
AI systems that can explain their decision-making processes and reasoning to human users.
Category: Human Factors
Read more →F
4 terms
Few-Shot Learning
The ability of AI models to learn new tasks with only a small number of training examples.
Category: Learning Methods
Read more →Fine-tuning
A post-training technique to specialize a trained model on specific data for a particular task.
Category: Learning Methods
Read more →Fine-tuning
A post-training technique to specialize a trained model on specific data for a particular task.
Category: Learning Methods
Read more →Foundation Model
Large-scale AI models trained on diverse data that serve as the basis for various downstream applications.
Category: Advanced Concepts
Read more →G
3 terms
Gen AI (Generative AI)
AI systems that create new content—text, images, code, audio, or video—by learning patterns from data.
Category: Applications
Read more →Generative AI
AI systems capable of creating new content such as text, images, audio, or code based on learned patterns.
Category: Applications
Read more →GPT (Generative Pre-trained Transformer)
A family of language models that generate human-like text using transformer architecture.
Category: Core Technologies
Read more →H
3 terms
Hallucination
When an AI model generates false or misleading information that appears plausible but is factually incorrect.
Category: Challenges
Read more →Human-Agent Interaction
The study and design of interfaces and interactions between humans and AI agents.
Category: Human Factors
Read more →Human-in-the-Loop (HITL)
A system design pattern that combines human intelligence with AI intelligence, particularly for critical decisions or ambiguous situations.
Category: Human Factors
Read more →I
3 terms
Inference
The process of a trained AI model generating a response or making a prediction based on new input.
Category: Core Concepts
Read more →Inference
The process of a trained AI model generating a response or making a prediction based on new input.
Category: Core Concepts
Read more →Intent Recognition
The ability of AI systems to understand and classify the purpose or goal behind user inputs.
Category: Technical Capabilities
Read more →K
1 term
Knowledge Base
A structured repository of information that AI systems can access to provide accurate and relevant responses.
Category: Data & Knowledge
Read more →L
2 terms
LangChain
An open-source framework for developing applications powered by large language models (LLMs).
Category: Developer Tools
Read more →LLM (Large Language Model)
A large-scale neural network trained to understand and generate human language.
Category: Core Concepts
Read more →M
4 terms
MCP (model context protocol)
An open standard that allows AI models to interact with external tools like calendars, CRMs, or codebases easily and securely.
Category: Developer Tools
Read more →MCP (model context protocol)
An open standard that allows AI models to interact with external tools like calendars, CRMs, or codebases easily and securely.
Category: Developer Tools
Read more →Model
An AI model is a computer program built to work like a human brain, processing input to generate a response.
Category: Core Concepts
Read more →Model
An AI model is a computer program built to work like a human brain, processing input to generate a response.
Category: Core Concepts
Read more →P
3 terms
Post-training
Additional steps taken after a model's initial training is complete to make it more useful.
Category: Learning Methods
Read more →Post-training
Additional steps taken after a model's initial training is complete to make it more useful.
Category: Learning Methods
Read more →Prompt Engineering
Crafting inputs that elicit more accurate or useful outputs from AI models.
Category: Developer Tools
Read more →R
3 terms
RAG (Retrieval-Augmented Generation)
A technique that injects fresh, external knowledge into LLM prompts at run-time.
Category: Technical Capabilities
Read more →RLHF (reinforcement learning from human feedback)
A post-training technique to align AI models with human preferences using feedback.
Category: Learning Methods
Read more →RLHF (reinforcement learning from human feedback)
A post-training technique to align AI models with human preferences using feedback.
Category: Learning Methods
Read more →S
4 terms
Supervised learning
A type of machine learning where a model is trained on labeled data with correct answers provided.
Category: Learning Methods
Read more →Supervised learning
A type of machine learning where a model is trained on labeled data with correct answers provided.
Category: Learning Methods
Read more →Synthetic data
Artificially generated data that mimics the patterns and structure of real-world data.
Category: Data & Knowledge
Read more →Synthetic data
Artificially generated data that mimics the patterns and structure of real-world data.
Category: Data & Knowledge
Read more →T
5 terms
Token
The basic unit of text that an AI model processes, which can be a word or part of a word.
Category: Core Concepts
Read more →Token
The basic unit of text that an AI model processes, which can be a word or part of a word.
Category: Core Concepts
Read more →Training/Pre-training
The process by which an AI model learns by analyzing massive amounts of data.
Category: Learning Methods
Read more →Training/Pre-training
The process by which an AI model learns by analyzing massive amounts of data.
Category: Learning Methods
Read more →Transformer
The neural-network architecture that introduced ‘attention’ and enabled today’s LLM revolution.
Category: Core Technologies
Read more →U
2 terms
Unsupervised learning
A type of machine learning where a model is given unlabeled data to find patterns on its own.
Category: Learning Methods
Read more →Unsupervised learning
A type of machine learning where a model is given unlabeled data to find patterns on its own.
Category: Learning Methods
Read more →V
3 terms
Vibe coding
Building applications using AI tools by describing what you want in plain English (prompts) rather than writing code.
Category: Developer Tools
Read more →Vibe coding
Building applications using AI tools by describing what you want in plain English (prompts) rather than writing code.
Category: Developer Tools
Read more →Vibe marketing
A marketing approach that uses AI-generated, meme-friendly content to create authentic ‘vibes’ and social buzz.
Category: Marketing Techniques
Read more →Z
1 term
Zero-Shot Learning
The ability of AI models to perform tasks without having seen specific examples during training.
Category: Learning Methods
Read more →Showing all 62 terms