AI dictionary, served simply.

Adaptive / Extended thinking

A mode that gives an AI more reasoning time for difficult or multi-step problems.

Agent authorization

Checking whether a particular AI agent may take a particular action on a particular resource under the current rules.

Agent containment

Technical limits that control what an AI agent can access, change, send, or spend while it works.

Agent evaluations

Repeatable tests that check whether an AI agent completes tasks correctly and follows its rules before or while people use it.

Agent kill switch

An operator-controlled way to quickly stop an AI agent's actions or access when it malfunctions or creates risk.

Agent observability

Tracking an AI agent's steps, tool use, errors, speed, quality signals, and cost so people can understand and improve its behavior.

Agent registry

A searchable catalog that records which AI agents exist, who owns them, what they can do, and where they are in their life cycle.

Agent sandbox

An isolated workspace where an AI agent can use approved files, tools, and network connections without open access to the host system.

Agent sprawl

When an organization creates AI agents faster than it can track their owners, purposes, permissions, costs, and results.

Agent2Agent Protocol (A2A)

An open standard that lets independent AI agents discover one another, exchange messages, and work together across different systems.

Agentic browsing

When an AI uses a web browser to navigate pages and take actions for a person instead of only returning search results.

Agentic coding

Using an AI coding agent that can inspect files, edit code, run tools and tests, and correct its work across multiple steps.

Agentic commerce

Shopping or business buying in which an AI agent helps find, compare, or purchase goods and services on a person's or company's behalf.

AI agent

An AI system that can plan steps, use tools, and take actions toward a goal.

AI alignment

Work intended to make AI behavior better match human goals, values, instructions, and safety needs.

AI Grounding

Giving an AI trusted, relevant information such as documents, database records, or search results so its answer stays connected to real sources.

AI model

A mathematical system trained on data to perform tasks such as writing, translating, or classifying.

AI slop

Low-quality text, images, or video made with AI and published mainly for volume or attention.

AI tool

An application or service that lets people use an AI model to complete a task.

AI wrapper

Software placed around a model to give it a friendlier interface, instructions, tools, or controls.

An AI agent with a standing goal that can track progress and resume approved work after a conversation ends when a schedule, event, or new information calls for action. ChatGPT dots are one example of this type of agent.

API (Application Programming Interface)

A defined way for software systems to send requests and exchange information.

API keys

Secret codes that let an app prove it has permission to use an API or online service.

Artifacts

Documents, code, applications, or designs created in a separate workspace beside the conversation.

Artificial intelligence (AI)

When computers are designed to learn, decide, create, or solve problems that normally require human intelligence.

Branch

A separate version of a project where you can work on changes without disturbing the main version.

Browser Control

A capability that lets an AI or automation operate a web browser by opening pages, clicking buttons, typing into fields, and scrolling.

Chat

A conversational interface where you send messages to an AI assistant and receive responses.

Chatbot

A program that communicates through text or voice to answer questions or perform tasks.

ChatGPT

OpenAI’s conversational AI product for asking questions, creating content, analyzing information, and using tools.

ChatGPT dots

Always-on AI agents in ChatGPT that can keep working on goals between conversations and ask you to review results or make decisions.

Claude AI

Anthropic’s family of AI assistants for conversation, writing, analysis, coding, and tool use.

Claude Code

A coding environment where Claude can inspect, build, test, and debug software with tools.

Claude Design

A design-focused workflow for creating layouts, visuals, and web experiences with AI assistance.

Claude in Excel / PowerPoint / Chrome

Ways Claude can assist directly inside spreadsheets, presentations, and browser workflows.

Client Portal

A private online space where clients sign in to view project updates, share files, send messages, or manage services with a business.

Cloud Browser

A web browser that runs on a remote server and is accessed over the internet, rather than running on your own device.

Cloud computing

Using rented computing power and storage over the internet instead of owning every server.

Codex

OpenAI's AI coding agent that helps build software by reading, writing, reviewing, and debugging code.

COF / tool chain

A coordinated set of tools and services that work together to deliver an AI solution.

Commit

A saved checkpoint that records a specific set of changes to a project.

Computer Use

A capability that lets an AI interact with visible software by clicking, typing, and navigating.

Connectors

Bridges that let an AI system access approved information or actions in another service.

Context engineering

Selecting and organizing what goes into an AI model’s context window, such as instructions, documents, conversation history, and tool results, so it has the right information for the task.

Context window

The maximum amount of information a model can consider at one time.

Conversational AI tool

An AI system that understands everyday language and responds in a conversation.

Cowork

A collaborative mode where Claude can help carry out organized, multi-step work like a teammate.

Custom instructions

Specific guidance that tells an AI how to behave for a particular project or workflow.

Data stores

Systems that hold information an AI agent can retrieve, such as current records, past data, or reference documents.

Dataset

An organized collection of examples—such as text, images, or numbers—used to train or test AI.

Decision model

An AI model built to choose from set options, answer yes or no, or assign a score instead of writing an open-ended response.

Deep learning

A type of machine learning that uses many-layered neural networks to find complex patterns in text, images, or sound.

Dispatch

A mobile workflow for sending and following tasks from a phone to a larger AI workspace.

Durable execution

Saving an AI agent's progress so an interrupted multi-step run can resume safely without starting over or repeating completed work.

Explainability

Making an AI system’s reasoning or decision factors understandable enough to review and question.

Fine-tuning

Extra focused training that adapts a general model for a particular task, subject, or style.

Forward deployed engineer (FDE)

An engineer who works alongside a customer to build and deploy software for the customer's real workflows, often connecting AI to existing systems.

Functions

Named, reusable pieces of code that perform specific actions; an AI agent can request a function by supplying the inputs it needs.

Generative AI (GenAI)

AI that creates new content such as text, images, code, music, or video.

Generative UI

An interactive screen that an AI assembles for the current task instead of giving only a fixed page or plain-text answer.

GitHub Actions

Automated jobs that run steps such as tests, builds, or deployments when a project changes.

GitHub Copilot

An AI coding assistant that suggests code and explains options while you work.

GitHub repository

A project folder on GitHub that stores a project’s code, files, and history in one shared place.

Global instructions

High-level preferences that shape how an AI assistant responds across tasks.

GPT (Generative Pre-trained Transformer)

A family of language models pre-trained on large datasets to understand and generate language.

GPT-4 / GPT-5

Generations of GPT models with different levels of reasoning, capability, speed, and tool use.

GPTs / wrappers

Customized experiences built around a general model using extra instructions, knowledge, interfaces, or tools.

GPU (Graphics Processing Unit)

A chip designed for many calculations at once, making AI training and inference faster.

Graph engineering

Designing how agents or workflow steps connect, share information, and hand off tasks to form a coordinated system.

Hallucination

An AI response that sounds confident but contains incorrect, misleading, or invented information.

Harness engineering

Building the tools, guardrails, and saved progress around an AI model so an agent can act, follow boundaries, and resume work reliably.

Human-in-the-loop

Keeping a person involved to guide, approve, or correct an AI system’s work.

Inference

The moment a trained model uses what it learned to answer a new question or make a prediction.

Issue

A tracked task, question, bug, or improvement that the project team needs to discuss or fix.

Knowledge base

An organized collection of trusted information that an AI system can search or reference.

Language processing / NLP

Techniques that help computers read, analyze, translate, and generate human language.

Large language model (LLM)

A model trained on huge amounts of text so it can predict language and generate fluent responses.

Loop engineering

Designing how one AI agent repeatedly chooses an action, uses a tool, checks the result, and continues until it finishes, reaches a limit, or needs help.

Machine learning (ML)

A way for computers to learn patterns from data instead of following only hand-written rules.

Markdown

A lightweight text format that uses simple symbols for headings, lists, links, and emphasis.

Memory

Information an AI assistant is allowed to retain to personalize future conversations and work.

Model Context Protocol (MCP)

An open standard that lets an AI app connect to outside tools, data, and services through one consistent setup.

Multi-agent applications

Applications that use two or more AI agents with different roles to work on parts of a task and bring their results together.

Natural language

The everyday way people speak and write, rather than computer code.

Neural network

A system of connected mathematical units that work together to recognize patterns.

Non-human identity (NHI)

A digital identity and set of permissions assigned to software, automation, or an AI agent instead of a person.

Open source

Software whose source code is available under a license that lets people use, study, change, and share it.

Open-weight AI Models

AI models whose trained weights are available for developers to download, inspect, adapt, and run, depending on the model’s license.

OpenAI

The AI research and product company that develops GPT models, ChatGPT, and related tools.

Opus, Sonnet, Haiku

Names used for different Claude model tiers, balancing capability, speed, and cost.

Output

The answer or content an AI returns after receiving a prompt.

Playground

A developer interface for experimenting with model prompts, settings, and responses.

Plugins

Packages that add focused capabilities, tools, connections, or workflows to an AI system.

Pre-training

The first large training stage where a model learns broad patterns from a huge dataset.

Projects

Organized workspaces that group related conversations, files, and instructions around one goal.

Prompt

The message, question, or instructions you give an AI model to explain what you want.

Prompt chaining

A technique for getting more complex and nuanced results from large language models like Gemini by using the output of one prompt as input to the next. It is like a conversation where each response builds upon the previous one, helping produce a more sophisticated and refined outcome.