Word shelf

Agent

An AI loop that plans, uses tools, observes, and continues toward a goal.

AI copyright

AI copyright concerns how copyright law applies to AI training data, generated outputs, and human authorship.

AI monitoring

AI monitoring tracks a deployed AI system's quality, reliability, safety, and operational performance.

Chain-of-thought prompting

Chain-of-thought prompting asks a model to work through intermediate reasoning steps before giving an answer.

Clustering

Clustering is an unsupervised learning method that groups data points by similarity.

Decision tree

A decision tree predicts an outcome by applying a sequence of feature-based splits.

Deep learning

Deep learning uses multilayer neural networks to learn representations and patterns from data.

Embedding

Numbers that represent the meaning of text so computers can compare ideas.

Fine-tuning

Git

Git is a distributed version control system for tracking and combining changes to files.

GitHub

GitHub is a platform for hosting Git repositories and collaborating on software.

Inference

LLM

A Large Language Model predicts the next piece of text from patterns it learned.

Loss function

A loss function measures how far a model's predictions are from the desired outcomes during training.

MCP

A standard way to plug tools and data into AI apps — like USB for AI capabilities.

Model serving

Model serving makes a trained model available to applications for inference, usually through an API.

Multi-agent system

A multi-agent system coordinates multiple autonomous agents that interact to pursue shared or separate goals.

Multimodal

Production AI architecture

Production AI architecture is the system design that connects models, data, applications, infrastructure, and operational controls.

Prompt injection

RAG

Retrieve relevant documents first, then generate an answer from them.

Random forest

A random forest combines many randomized decision trees to produce a more robust prediction.

RLHF

Speech recognition

Speech recognition converts spoken language in audio into text.

Token

A small chunk of text the model reads and writes.

Tool / function calling

Let an AI app run real actions (weather, calendar, API) instead of only chatting.

Transformer

A **transformer** is the architecture behind modern LLMs. Its **attention** mechanism weighs which earlier tokens matter most when predicting the next one.

Vector

A list of numbers that can be treated like a point in space.

Virtual environment

A virtual environment isolates a Python project's packages and versions from other projects and the system installation.