Glossary

Definitions of terms used in the curriculum.

Showing 81–120 of 902 terms in the glossary

Letter A19 terms

A record

  • DNS
A DNS entry that maps a hostname to the server’s IPv4 address so traffic reaches your app.

acceptEdits

  • Concepts
A permission mode that auto-approves file edits and common filesystem commands (mkdir, touch, rm, mv, cp, sed) without prompting, while still asking before other shell commands.

Action

  • Workflows
A step a Zap performs after the trigger — create, update, or send something in another app.

Action node

  • Concepts
A node that does something in an external service — such as creating a row in Google Sheets, sending a Slack message, or reading an email.

Action Prompt

  • Interface
A field where you type a short command (e.g., “walk across the screen”) to make the avatar perform that motion.

Actions

  • Concepts
Onyx's mechanism for letting an agent call external applications (with flexible authentication), so a chat can do things — look up or update a record — not just retrieve documents.

Actions tab

  • Interface
The page in a GitHub repository that shows the history and details of automated workflows that have run.

Add Source

  • Interface
Button in the interface that lets you attach a new document or web page to the current notebook.

Add Space

  • Interface
A button that lets you select or upload a background image for an avatar’s scene.

add tools method

  • Command
  • Methods
A function call on the WebSocket connection that registers your custom tool schemas so the Realtime model can invoke them during a conversation.
3 other definitions

add tools method · Command

A LiveKit function you call on the WebSocket to register custom tool definitions so the model can invoke them during a voice session.

add tools method · Methods

A LiveKit command used on an open WebSocket connection to register your custom tool schemas so the model can invoke them.

add tools method · Methods

A function you call on the WebSocket connection to register custom tool definitions so the model can invoke them.

Advanced Voice

  • Features
A mode that lets you speak to ChatGPT and hear it respond in a natural-sounding voice, available on the ChatGPT website, iOS, Android, and Windows app.

Agent

  • Components
  • Concepts
  • Core
An AI system that does more than answer: it plans steps towards a goal, uses tools such as search or files, checks the result and carries on. Give it only the access the task needs.

Also known as: agent, AI agent

5 other definitions

Agent · Concepts

An AI process that Antigravity launches to carry out a task — it can read files, run code, browse the web, and make changes autonomously.

Agent · Concepts

A Dify application type where the AI can reason, decompose tasks, and call tools on its own without you having to pre-define every step.

Agent · Concepts

An autonomous AI component that can reason, plan, decide which tools to use, and take actions — unlike a plain LLM node, it makes decisions dynamically.

agent · Components

A pre‑configured chatbot you can train with documents and rules to perform a specific task, like writing LinkedIn posts.

agent · Concepts

A named AI assistant profile in opencode with its own set of instructions, permitted tools, and optionally a specific model — for example a 'Plan' agent that cannot edit files.

Agent mode

  • Concepts
A mode where Cursor autonomously reads your project and writes changes across multiple files in one session, rather than answering a single question.

Agent Skills

  • Concepts
The open standard for the skill format (a folder + SKILL.md). It began at Anthropic and is read by many tools, so one skill works across them.

Agent Span

  • Concepts
A service that moves the state of an AI agent to its own server so the agent can continue after crashes and be inspected via a web interface.

agent_span server start

  • Commands
The command line instruction that launches the Agent Span server on the default port 6767.

Agentflow

  • Concepts
Flowise's most powerful visual builder — a superset of both Chatflow and Assistant — that supports multi-agent systems, branching logic, loops, and human-in-the-loop checkpoints.

agentic

  • Concepts
Describes AI that plans and carries out a multi-step job itself — opening files, using apps, checking its work — rather than just answering a single prompt.

Agentic features

  • Concepts
Autonomous capabilities where v0 plans and carries out multi-step tasks on its own — such as running terminal commands, searching the web, fixing errors, and calling external integrations — without you directing every step.

Symbols21 terms

/usage

  • Slash commands
Shows session cost, plan usage limits, and activity statistics, including a breakdown by skill, subagent, and MCP server on paid plans.

/v1/

  • Files & config
The URL prefix for Ollama's OpenAI-compatible API, which lets software written for OpenAI's API talk to your local Ollama models instead.

/validate

  • Commands
Runs the checks that must pass — lint, type-check and tests — and reports what failed.

/var/run/docker.sock

  • Files
A Unix socket file through which the Docker CLI talks to the Docker daemon; access gives full control over Docker.

`--platform linux/amd64`

  • Commands
A flag you add to a Docker pull or run command to tell Docker to emulate an Intel‑based image on Apple Silicon.

`COPY <source> <dest>`

  • Commands
A line you add to a Dockerfile to copy files from your Mac into the image during build, improving performance on Apple Silicon.

`docker --version`

  • Commands
A Terminal command that prints the installed Docker version, confirming the CLI is available.

`docker system prune -a`

  • Commands
A command that deletes all unused images, containers, networks, and build cache to free disk space.

`ssh root@<ip>`

  • Commands
A command that opens a secure shell session as the root user on the server whose IP replaces .

+ New Repository button

  • Interface
The web UI control in Gitea used to start a new repository without using the command line.

<break time="1.5s"/>

  • Settings
An inline tag you insert in your script to make the generated speech pause for the specified number of seconds.

<context>

  • Concepts
An XML-style tag you wrap around background information in a Claude prompt so Claude can clearly distinguish it from your instructions or question.

<data>

  • Concepts
An XML tag used to enclose raw data (such as a table or CSV snippet) inside a prompt so Claude can tell it apart from your instructions and context.

<task>

  • Concepts
An XML tag recommended by Anthropic for wrapping the specific instruction you want Claude to carry out, keeping it distinct from background context in the same prompt.

>>>

  • Concepts
The prompt symbol Ollama shows when it is waiting for you to type a message inside an interactive chat session.

~/.claude/CLAUDE.md

  • Files & config
Your personal, global rules that apply across all of your projects. The ~ means your home folder.

~/.codex/AGENTS.md

  • Files & config
A personal instructions file Codex reads before every session — write it in plain English to tell Codex about your preferences, coding style, or recurring context.

~/.codex/config.toml

  • Files & config
The main user-level configuration file for Codex, stored in your home directory, where you set durable defaults like model, MCP servers, and feature flags.

~/.hermes/.env

  • Files & config
  • Files & Config
A hidden file holding secrets like API keys, kept out of the main config.
2 other definitions

~/.hermes/.env · Files & Config

A hidden environment-variable file inside the Hermes config folder where you can store API keys and secrets separately from the main config file.

~/.hermes/.env · Files & config

A file in your Hermes Agent folder that stores secret values such as API keys, kept separate from the main config file so credentials are not accidentally shared.

~/.hermes/config.yaml

  • Files & config
  • Files & Config
Hermes’s main settings file — which provider, model and server it uses. The ~ means your home folder.
2 other definitions

~/.hermes/config.yaml · Files & Config

The main configuration file for the Hermes tool, stored in a hidden folder in your home directory — you edit it to point Hermes at your local LM Studio server.

~/.hermes/config.yaml · Files & config

The main configuration file for Hermes Agent, stored in a hidden folder in your home directory, where you set the model provider, base URL, and other non-secret preferences.

0.0.0.0

  • API & URLs
A special network address meaning 'listen on all network interfaces' — when LM Studio binds to this (via lms server start --bind 0.0.0.0), devices on your local Wi-Fi or wired network can connect to it, not just your own computer.