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.
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.
AI Hallucination
A hallucination is an LLM output that is fluent and plausible but factually incorrect or unsupported by any reliable source.
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.
EEAT
EEAT is a quality assessment framework — Experience, Expertise, Authoritativeness and Trustworthiness — used to guide how content, and the sites and authors producing it, are evaluated for credibility.
Generative Engine Optimisation
GEO is the set of editorial and technical practices that increase the likelihood a page is retrieved, quoted or cited by generative AI systems when they answer a user's question.
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.
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.
Prompt Engineering
Prompt engineering is the discipline of designing inputs to a language model so its outputs are accurate, useful and repeatable.
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.
Backlink
A backlink is a link from a page on one website to a page on a different website, used by search engines as one signal of the linked page's credibility and relevance.
Generative Engine Optimisation
GEO is the set of editorial and technical practices that increase the likelihood a page is retrieved, quoted or cited by generative AI systems when they answer a user's question.
Kanban
Kanban is a visual workflow management method that represents tasks as cards moving through columns on a board, with limits placed on work-in-progress to expose bottlenecks and keep flow steady.
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.
OCR
OCR is a computer vision technique that identifies characters within an image and converts them into digital, machine-readable text that can be searched, edited or processed by other software.
Prompt Engineering
Prompt engineering is the discipline of designing inputs to a language model so its outputs are accurate, useful and repeatable.
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.
Prompt Chaining
Prompt chaining is a prompting strategy that splits one large task into a sequence of smaller prompts, feeding each step's output forward as the next step's input.
System Prompt
A system prompt is a hidden or fixed instruction set passed to a language model that establishes its persona, rules and constraints before any user input is processed.
Function Calling
Function calling is a feature of modern language models that allows them to output a structured request to invoke a predefined function, with the calling application executing it and returning the result to the model.
Vision Model
A vision model is a neural network trained to process and interpret visual data, such as photographs, screenshots or diagrams, often paired with a language model so it can describe or reason about that visual content in text.
SLM
An SLM is a language model built with a smaller parameter count and training footprint than large flagship models, optimised for efficiency, low latency and deployment on limited hardware rather than maximum general capability.
Temperature
Temperature is a numerical parameter, typically between 0 and 2, that adjusts how a language model samples from its predicted probabilities for the next word, controlling the balance between predictability and variation in its output.
Prompt Chaining
Prompt chaining is a prompting strategy that splits one large task into a sequence of smaller prompts, feeding each step's output forward as the next step's input.
System Prompt
A system prompt is a hidden or fixed instruction set passed to a language model that establishes its persona, rules and constraints before any user input is processed.
Function Calling
Function calling is a feature of modern language models that allows them to output a structured request to invoke a predefined function, with the calling application executing it and returning the result to the model.
Vision Model
A vision model is a neural network trained to process and interpret visual data, such as photographs, screenshots or diagrams, often paired with a language model so it can describe or reason about that visual content in text.
SLM
An SLM is a language model built with a smaller parameter count and training footprint than large flagship models, optimised for efficiency, low latency and deployment on limited hardware rather than maximum general capability.
Temperature
Temperature is a numerical parameter, typically between 0 and 2, that adjusts how a language model samples from its predicted probabilities for the next word, controlling the balance between predictability and variation in its output.
For gaming networking, latency optimisation, ping reduction and competitive networking concepts, visit our dedicated Gaming Networking Glossary — a beginner-first learning centre covering latency, routing, diagnostics and optimisation.
Explore the Gaming Networking Glossary →ACH
ACH is a US batch-based electronic funds transfer network, operated under NACHA rules, that moves money between bank accounts for payroll, bill payments, direct debits and vendor payouts.
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.
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.
AI Hallucination
A hallucination is an LLM output that is fluent and plausible but factually incorrect or unsupported by any reliable source.
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.
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.
API
An API (Application Programming Interface) is a defined set of endpoints and rules that lets one program request functionality or data from another.
Backlink
A backlink is a link from a page on one website to a page on a different website, used by search engines as one signal of the linked page's credibility and relevance.
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.
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.
CI/CD
CI/CD is a set of automated practices and tools that build, test and release software every time code changes, reducing the manual effort and risk involved in shipping updates.
Container
A container is a standardised, isolated unit of software that packages an application together with its dependencies, sharing the host operating system's kernel rather than running a full separate operating system.
Core Web Vitals
Core Web Vitals are a defined set of metrics measuring real-world page loading speed, interactivity responsiveness and visual layout stability, used as one signal in search engine page-quality assessments.
Crawl Budget
Crawl budget is the combination of crawl rate limit (how fast a search engine can fetch pages without overloading the server) and crawl demand (how many pages the engine wants to fetch based on perceived value) for a given site.
DNS Leak
A DNS leak is a failure mode in which DNS lookup requests — the translations of domain names into IP addresses — are sent to a default, unencrypted DNS server outside the VPN tunnel, revealing browsing destinations despite an active VPN connection.
Docker
Docker is a software platform that lets developers build, distribute and run applications inside containers, providing a consistent runtime environment across different machines.
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.