AI Common Terms

AI tutorials use many repeated words.

This page is a simple glossary so you can revise the important terms quickly.


🤔 Why Learn These Terms?

When you read AI documentation, you will often see words such as:

If these words are unclear, AI applications feel confusing.

So let’s keep the meanings simple.


📋 Common Terms

TermSimple meaning
AITechnology that enables computers to perform tasks that normally require human intelligence.
Machine LearningA way of building AI systems where computers learn patterns from data.
Deep LearningA type of Machine Learning that uses neural networks with multiple layers.
Neural NetworkA model structure inspired by connected processing units called neurons.
TransformerA neural-network architecture that uses attention to process relationships in a sequence.
LLMLarge Language Model; a model that processes and generates language.
TokenA small piece of text processed by a language model.
TokenizationThe process of breaking text into tokens.
ParameterA learned numerical value inside a model.
ContextInformation available to the model for the current request.
Context WindowThe maximum amount of context a model can handle for a request.
InferenceUsing a trained model to produce an output.
TemperatureA generation setting that affects how varied the output can be.
HallucinationAn incorrect or unsupported answer that sounds confident.
PromptThe input or instruction given to an AI model.
EmbeddingA vector representation created by a model to capture useful relationships.
RAGRetrieval-Augmented Generation; retrieve relevant information, then generate an answer.
ToolAn external capability an AI application can call.
AgentAn AI workflow that can plan steps and use tools.

📋 Terms That Are Easy to Confuse

Token vs Parameter

Token

Input or output text piece

Parameter

Learned value inside the model

They are completely different concepts.


Context vs Training

Context is information given during the current request.

Training is the process that changes model parameters.

Context

Available now

Training

Changes the model


Prompt vs Context

A prompt is the instruction or input we give.

Context is the broader information available to the model for that request.

A prompt can be part of the context.


RAG vs Fine-Tuning

RAG gives information to the model at request time.

Fine-tuning changes model behaviour through additional training.

RAG

Provide relevant context

Fine-tuning

Update model behaviour


🧩 Key Points


🚀 What Comes Next?

Now we can move from fundamentals to building a simple LLM application.