Term Library

Search by name, definition, or keyword. Filter by category and difficulty, then sort A–Z or by how tricky a word is.

Up to difficulty
5/5

30 terms

Agent

Agents

AY-jent

An AI worker that has a specific job to do.

1/5 · Easy

Algorithm

Fundamentals

AL-go-rith-um

A list of steps that tells a computer how to solve a problem.

2/5 · Getting there

API

Infrastructure

A-P-I

A doorway that lets two pieces of software talk to each other.

3/5 · Trickier

Automation

Infrastructure

aw-toh-MAY-shun

Setting up work so it happens by itself, without someone doing it each time.

1/5 · Easy

Autonomous Agent

Agents

aw-TON-oh-mus AY-jent

An AI agent that can complete tasks on its own within rules you give it.

4/5 · Advanced

Benchmark

Fundamentals

BENCH-mark

A standard test used to compare how well different AI models perform on the same task.

2/5 · Getting there

Calibration

Fundamentals

kal-ih-BRAY-shun

Adjusting an AI system so its answers become more accurate and reliable.

3/5 · Trickier

Context Window

Models

KON-text WIN-doh

How much information an AI can hold in mind at one time.

3/5 · Trickier

Embedding

Data

em-BED-ing

Turning words or documents into numbers so a computer can tell which ones mean similar things.

4/5 · Advanced

Fine-Tuning

Models

FYNE TOON-ing

Extra training that teaches a general AI the specifics of your work.

3/5 · Trickier

Guardrails

Fundamentals

GARD-rayls

The rules and limits you set so an AI stays safe and on task.

2/5 · Getting there

Hallucination

Fundamentals

huh-LOO-sih-NAY-shun

When an AI confidently gives an answer that is simply made up.

2/5 · Getting there

Human in the Loop

Agents

HYOO-mun in the LOOP

A setup where a person reviews or approves what the AI does before it counts as final.

2/5 · Getting there

Inference

Models

IN-fer-ens

Inference is when an AI uses what it has already learned to answer a question, make a prediction, or complete a task.

1/5 · Easy

Latency

Infrastructure

LAY-ten-see

The delay between asking an AI something and getting the answer back.

2/5 · Getting there

Machine Learning

Fundamentals

muh-SHEEN LURN-ing

A way of teaching a computer by showing it lots of examples instead of writing out every rule.

2/5 · Getting there

Model

Models

MOD-ul

The AI's brain that has learned from lots of information.

2/5 · Getting there

Multi-Agent System

Agents

MUL-tee AY-jent SIS-tem

Many AI agents working together while sharing information.

3/5 · Trickier

Multimodal

Models

muhl-tee-MOH-dul

An AI that can handle more than one kind of input — text, images, audio, or video together.

3/5 · Trickier

Nano AI-Driven Ecosystem

Agents

NAN-oh A-I EE-koh-sis-tem

A group of very small AI programs that each have one job, but they work together like a team to solve bigger problems.

3/5 · Trickier

Neural Network

Models

NOOR-ul NET-wurk

A math structure loosely modeled on the brain, made of layers that pass signals along to spot patterns.

3/5 · Trickier

Orchestrator

Agents

OR-kes-tray-tor

The AI manager that tells all the other AI agents what to do.

3/5 · Trickier

Prompt

Fundamentals

PROMPT

The instructions or question you give an AI so it knows what you want.

1/5 · Easy

Prompt Engineering

Fundamentals

PROMPT en-jih-NEER-ing

The skill of writing instructions that get better answers from AI.

2/5 · Getting there

Retrieval-Augmented Generation (RAG)

Data

RAG

A method where the AI looks up your real documents before answering, instead of guessing.

4/5 · Advanced

Temperature

Models

TEM-pur-uh-chur

A setting that controls how predictable or creative an AI's answers are.

3/5 · Trickier

Token

Models

TOH-kun

A small chunk of text — roughly part of a word — that an AI reads and writes one piece at a time.

2/5 · Getting there

Training Data

Data

TRAY-ning DAY-ta

The information an AI studied in order to learn.

2/5 · Getting there

Vector Database

Data

VEK-tor DAY-ta-base

A special kind of memory that helps AI quickly find information that is similar.

4/5 · Advanced

Vector Database

Infrastructure

VEK-tor DAY-tuh-bays

A place to store embeddings so an AI can quickly find the most similar pieces of your content.

4/5 · Advanced