AI Glossary · 25 terms and growing

AI Glossary

Learn the language of Artificial Intelligence with The Tool Money Lab's growing library of clear, jargon-free explanations — written for founders, operators and curious professionals.

Featured concepts
beginner7 min read

AI Agent

An AI agent is a language-model-powered system that plans and executes multi-step tasks by choosing which tools or APIs to call in order to reach a user-defined goal.

Read definition →
beginner5 min read

AI Hallucination

A hallucination is an LLM output that is fluent and plausible but factually incorrect or unsupported by any reliable source.

Read definition →
beginner5 min read

Context Window

The context window is the token budget an LLM can read and write within a single request, covering the prompt, retrieved data, previous turns and the response itself.

Read definition →
beginner7 min read

LLM

An LLM is a neural network trained on very large text datasets to predict the next token in a sequence, which enables general-purpose language understanding and generation.

Read definition →
intermediate6 min read

MCP (Model Context Protocol)

The Model Context Protocol is an open standard for connecting AI models to external tools, data and services through a shared JSON-RPC interface.

Read definition →
beginner6 min read

Prompt Engineering

Prompt engineering is the discipline of designing inputs to a language model so its outputs are accurate, useful and repeatable.

Read definition →
intermediate8 min read

Retrieval-Augmented Generation (RAG)

Retrieval-Augmented Generation is a pattern in which relevant documents are retrieved from an external source and injected into an LLM's prompt so the model can answer with grounded, up-to-date, private information.

Read definition →
Most popular
Newest entries
Recently updated
Browse by category
Beginner concepts
beginner7 min read

AI Agent

An AI agent is a language-model-powered system that plans and executes multi-step tasks by choosing which tools or APIs to call in order to reach a user-defined goal.

Read definition →
beginner4 min read

AI Automation

AI automation is the use of AI models to perform tasks — usually language, vision or decision tasks — that were previously done manually because they required judgement.

Read definition →
beginner5 min read

AI Hallucination

A hallucination is an LLM output that is fluent and plausible but factually incorrect or unsupported by any reliable source.

Read definition →
beginner4 min read

AI Tokens

A token is the unit of text an LLM processes — typically 3-4 characters or roughly three-quarters of an English word. Prompts, replies and pricing are all measured in tokens.

Read definition →
beginner4 min read

AI Workflow

An AI workflow is an orchestrated sequence of steps in which one or more AI models cooperate with tools, APIs and human approvals to complete a task.

Read definition →
beginner4 min read

API

An API (Application Programming Interface) is a defined set of endpoints and rules that lets one program request functionality or data from another.

Read definition →
beginner5 min read

Context Window

The context window is the token budget an LLM can read and write within a single request, covering the prompt, retrieved data, previous turns and the response itself.

Read definition →
beginner4 min read

Few-shot Prompting

Few-shot prompting is a prompting technique that includes a small number of input/output examples in the prompt to steer the model toward the desired format or behaviour.

Read definition →
Intermediate & advanced
intermediate6 min read

Agentic AI

Agentic AI refers to systems where a language model autonomously decomposes goals, selects tools and executes multi-step actions with minimal human intervention.

Read definition →
intermediate5 min read

Chain-of-Thought Prompting

Chain-of-thought (CoT) prompting is a technique where the model is asked to produce intermediate reasoning steps before its final answer, improving performance on multi-step problems.

Read definition →
intermediate5 min read

Embeddings

An embedding is a dense vector produced by a model that maps content into a space where distance corresponds to semantic similarity.

Read definition →
intermediate6 min read

Fine-tuning

Fine-tuning is additional training applied to a pretrained model on curated examples so the model specialises in a task, tone, format or domain.

Read definition →
intermediate6 min read

MCP (Model Context Protocol)

The Model Context Protocol is an open standard for connecting AI models to external tools, data and services through a shared JSON-RPC interface.

Read definition →
advanced6 min read

Reinforcement Learning

Reinforcement learning is a machine learning paradigm in which an agent learns to make decisions by receiving reward signals for its actions in an environment.

Read definition →
intermediate8 min read

Retrieval-Augmented Generation (RAG)

Retrieval-Augmented Generation is a pattern in which relevant documents are retrieved from an external source and injected into an LLM's prompt so the model can answer with grounded, up-to-date, private information.

Read definition →
advanced6 min read

Transformer Model

A transformer is a neural network architecture built around self-attention, which enables efficient modelling of long-range dependencies in sequences.

Read definition →
Full A–Z index
Keep exploring
Intelligence Brief

Stay Ahead of AI

Receive our weekly Intelligence Brief. Independent AI reviews, comparisons, new tools and practical recommendations delivered every Friday.

  • New AI tools
  • Honest reviews
  • Best AI deals
  • New comparisons
  • Industry trends
  • No spam.