Software and AI glossary, in plain English

A

• AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
• AI copilot An AI copilot is an assistant built into a tool people already use, which suggests, drafts and explains while the person stays in control.
• API An API, or application programming interface, is a defined way for one piece of software to request data or actions from another.
• API integration An API integration connects two or more systems through their APIs so data and actions flow between them automatically.
• Artificial intelligence Artificial intelligence is the broad field of building software that performs tasks that normally need human judgment, such as understanding language or images.
• Automation Automation is using software to perform a task or process with little or no human effort each time it runs.

B

• Backend The backend is the part of an application that runs on servers, storing data, applying business rules and serving the frontend through APIs.
• Business process automation Business process automation uses software to run a multi-step business process, such as approvals or onboarding, from start to finish with less manual work.

C

• Chatbot A chatbot is software that holds a conversation with people through text or voice, answering questions or completing simple tasks.
• Claude Code Claude Code is Anthropic's agentic coding tool, which works in a developer's terminal, IDE, desktop app or browser to read code, run commands and make changes.
• Cloud hosting Cloud hosting runs websites and applications on servers rented from a provider, which can grow or shrink with demand.
• Context window A context window is the maximum amount of text, measured in tokens, that an AI model can consider at once, including the question, documents and its answer.
• CRM A CRM, or customer relationship management system, stores contacts, companies, deals and interactions so a team can manage its customer relationships in one place.
• Cross-platform app A cross-platform app is a mobile app built from one shared codebase that runs on both iOS and Android.

D

• Database A database is an organized store of data that software can search, update and keep consistent, such as customers, orders or bookings.
• Deployment Deployment is the process of releasing a new version of software to the servers where users can reach it.

E

• Embeddings Embeddings are lists of numbers that represent the meaning of text or images, so software can find items that are similar in meaning.

F

• Fine-tuning Fine-tuning is further training an existing AI model on your own examples so it learns a specific style, format or task.
• Frontend The frontend is the part of a website or app that people see and use, including pages, forms, buttons and how they respond.
• Function calling Function calling is a model feature that lets an AI model request a specific function, with structured inputs, for the application to run.

H

• Hallucination A hallucination is when an AI model states something false or invented as if it were true, such as a made-up fact, figure or source.
• Headless CMS A headless CMS is a content management system that stores and edits content but delivers it through an API, leaving the design to a separate frontend.

I

• Inference Inference is the step where a trained AI model is used to produce an output, such as an answer, a label or a prediction, from new input.

J

• JSON JSON is a simple text format for structured data, made of names and values, that most software and APIs use to exchange information.

L

• Large language model A large language model, or LLM, is an AI model trained on vast amounts of text that can understand and generate language, and often images and code.
• Latency Latency is the delay between a request and its response, such as how long a page takes to start loading or an AI model takes to reply.
• LLM integration LLM integration is connecting a large language model to your software and data, so AI features work inside your own products and processes.

M

• Machine learning Machine learning is a way of building software that learns patterns from data to make predictions or decisions, instead of following only hand-written rules.
• MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
• Model Context Protocol The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.
• Multi-tenant Multi-tenant describes software where one application and database serve many customers, called tenants, while keeping each customer's data separate.
• Multimodal model A multimodal model is an AI model that can take in more than one kind of input, such as text with images, audio or video.
• MVP An MVP, or minimum viable product, is the smallest version of a product that real users can use and pay for, built to learn quickly what works.

N

• Natural language processing Natural language processing is the field of AI that deals with understanding and generating human language, in text or speech.
• No-code No-code tools let people build apps, websites and automations with visual editors instead of writing code.

O

• OCR OCR, or optical character recognition, is technology that turns text in images and scanned documents into machine-readable text.
• Open-weights model An open-weights model is an AI model whose trained parameters are published, so anyone can download and run it on their own hardware under its license.

P

• Progressive web app A progressive web app, or PWA, is a website that works like an installed app, with offline use, home screen icons and notifications.
• Prompt A prompt is the instruction and context you give an AI model to get the output you want.
• Prompt engineering Prompt engineering is the practice of designing, testing and improving prompts so AI models produce reliable results for a specific task.

R

• RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
• Reasoning model A reasoning model is an AI model that works through a problem step by step before answering, trading speed and cost for better results on hard tasks.
• REST API A REST API is a common style of web API where systems use standard web requests, such as GET and POST, to read and change resources at specific URLs.
• Reverse proxy A reverse proxy is a server that sits in front of your applications, receiving visitors' requests and passing them to the right app, often adding security and caching.

S

• SaaS SaaS, or software as a service, is software delivered over the internet on a subscription, rather than installed and owned by each customer.
• Semantic search Semantic search finds results by meaning rather than exact words, so a search for "reset my login" can find an article titled "Forgot your password".
• SEO SEO, or search engine optimization, is the work of making a website easy for search engines to understand and useful enough to rank for the searches your customers make.
• Sprint A sprint is a short, fixed period, often one or two weeks, in which a development team builds and delivers an agreed set of work.
• Structured output Structured output is when an AI model returns its answer in a fixed format, such as JSON matching a schema, so software can use it reliably.
• System prompt A system prompt is the standing set of instructions an application gives an AI model, defining its role, rules and style for every conversation.

T

• Technical debt Technical debt is the future cost of shortcuts taken in software, such as quick fixes or missing tests, which make later changes slower and riskier.
• Token A token is a small piece of text, often part of a word, that AI models read and write, and that providers use to measure limits and pricing.
• Tool calling Tool calling is when an AI model asks the application to run a tool, such as a search or database lookup, and then uses the result in its answer.

U

• User authentication User authentication is how an application confirms who a user is, through passwords, sign-in links, single sign-on or other methods, before giving access.

V

• Vector database A vector database stores embeddings, lists of numbers that represent meaning, and quickly finds the ones most similar to a query.
• VPS A VPS, or virtual private server, is a rented virtual machine with its own resources, on which you can install and run your own software.

W

• Webhook A webhook is an automatic message one system sends to another's web address when something happens, such as a payment or a new order.
• Wireframe A wireframe is a simple sketch of a screen's layout and content, used to agree on structure before visual design and development begin.
• Workflow automation Workflow automation uses software to move work through a series of steps, such as routing, approvals and notifications, based on rules and events.

Z

• Zero-shot classification Zero-shot classification is sorting text or images into categories an AI model was not specifically trained on, using only the category names or descriptions.