AI Glossary
Quick, friendly definitions of AI terms from A to Z.
A
Agent
aka: AI Agent, Autonomous Agent
An AI system that can use tools, make decisions, and take actions to complete tasks autonomously rather than just answering questions.
AI (Artificial Intelligence)
aka: Artificial Intelligence, AI
Making machines perform tasks that typically require human intelligence—like understanding language, recognizing patterns, or making decisions.
API (Application Programming Interface)
aka: REST API, API Endpoint
A way for different software programs to talk to each other—like a menu of requests you can make to get AI to do something.
B
C
Constitutional AI
aka: CAI, Constitutional Training, Self-Critique
A safety technique where an AI is trained using a set of principles (a 'constitution') to critique and revise its own outputs, making them more helpful, honest, and harmless without human feedback on every response.
Context Window
aka: Context, Context Length, Window Size
How much text an AI can 'see' or 'remember' at once. Older messages fall off when the window fills up.
E
Embedding
aka: Vector, Vector Representation, Embeddings
A list of numbers that represents the meaning of text. Similar meanings have similar numbers, so computers can compare by 'closeness'.
Evaluation (Evals)
aka: Evals, Model Evaluation, Testing
Systematically testing an AI system to measure how well it performs on specific tasks or criteria.
F
Few-Shot Learning
aka: Few-Shot Prompting, In-Context Learning
Teaching an AI model by including a few examples in your prompt, without any formal training—the model learns the pattern from the examples you show.
Fine-Tuning
aka: Model Fine-Tuning, Transfer Learning
Taking a pre-trained AI model and training it further on your specific data to make it better at your particular task.
G
Grounding
aka: Grounded Generation, Factual Grounding
Connecting AI outputs to verified sources or real data to reduce hallucinations and ensure responses are factually accurate.
Guardrails
aka: Safety Guardrails, AI Guardrails, Policy Guardrails
Rules or filters that prevent AI from generating harmful, biased, or inappropriate content. Like safety bumpers.
H
I
L
LangChain
aka: LangChain.js, LangChain Python
An open-source framework for building applications with LLMs, providing tools for chaining prompts, managing memory, connecting to external tools, and building AI agents.
Latency
aka: Response Time, Inference Time
How long it takes for an AI model to generate a response after you send a request.
LlamaIndex
aka: LlamaIndex.ai, GPT Index
An open-source framework for building LLM applications with data connectors, indexing, and retrieval—particularly strong for RAG (Retrieval Augmented Generation) systems.
LLM (Large Language Model)
aka: Large Language Model, Language Model, LLM
AI trained on massive amounts of text to understand and generate human-like language. Powers chatbots, writing tools, and more.
M
Machine Learning (ML)
aka: ML, Machine Learning
A way to train computers to learn from examples and data, instead of programming every rule manually.
Model
aka: AI Model, ML Model
The trained AI system that contains all the patterns it learned from data. Think of it as the 'brain' that makes predictions or decisions.
O
P
Parameters
aka: Model Parameters, Weights
Numbers inside an AI model that get adjusted during training to improve accuracy. More parameters usually mean more capability.
Prompt
aka: Prompting, Prompt Engineering
The question or instruction you give to an AI. A good prompt is clear, specific, and gives context.
Prompt Injection
aka: Prompt Attack, Jailbreaking
A security vulnerability where users trick an AI into ignoring its instructions by inserting malicious commands into their prompts.
Q
R
RAG (Retrieval-Augmented Generation)
aka: Retrieval-Augmented Generation, RAG
A technique where AI searches your documents for relevant info, then uses it to generate accurate, grounded answers.
RLHF (Reinforcement Learning from Human Feedback)
aka: Reinforcement Learning from Human Feedback, RLHF, Human Feedback Training
A training method where humans rate AI outputs to teach the model which responses are helpful, harmless, and accurate.
S
T
Temperature
aka: Sampling Temperature, Randomness
A setting that controls how creative or random AI outputs are. Low = predictable and focused. High = creative and varied.
Token
aka: Tokens, Tokenization
A chunk of text (usually a word or part of a word) that AI processes. 'Chatbot' might be one token or split into 'chat' and 'bot'.
Tokenizer
aka: Tokenization, Token Encoding
A tool that breaks text into smaller pieces (tokens) that an AI model can process. Different models use different tokenizers, affecting how they count and understand text.
Tool (Function Calling)
aka: Function, Function Calling, Tool Use
A capability that allows an AI to call external functions or APIs—like searching the web, querying databases, or running calculations.
Top-p (Nucleus Sampling)
aka: Nucleus Sampling, Top-k, Sampling Strategy
A parameter that controls randomness in AI text generation by choosing from the smallest set of words whose probabilities add up to p%. Lower values (0.1-0.5) make output more focused; higher values (0.9-1.0) make it more creative.
Training
aka: Model Training, AI Training
The process of feeding data to an AI system so it learns patterns and improves its predictions over time.
Transformer
aka: Transformer Architecture, Transformer Model
A neural network architecture that revolutionized AI by using attention mechanisms to understand relationships between words, enabling modern LLMs.