Glossary

Definitions of terms used in the curriculum.

Showing 121–160 of 902 terms in the glossary

Letter A40 terms

agentic RAG

  • Concepts
Onyx's retrieval approach: instead of one search, AI agents plan and run multiple retrieval steps over your connected sources, combining hybrid search and contextual retrieval for a more accurate, cited answer.

agentic workflow

  • Concepts
A design where the AI autonomously takes multiple steps — calling tools, browsing data, making decisions — to complete a goal rather than answering a single question.

Agents

  • AI
Zapier AI agents that carry out multi-step tasks such as research or data lookups.

AGENTS.md

  • Files
  • Files & config
A plain-text file you place in your project folder (or home config folder) that gives the AI standing instructions about your project's structure, coding conventions, and quirks.

Also known as: agents.md

1 other definition

agents.md · Files

A markdown file placed in a project folder that contains a permanent system prompt defining the agent’s role, business context, and tool instructions.

agents.yaml

  • Files & config
A CrewAI configuration file (in YAML format) where you describe each agent's role, goal, and backstory without writing Python code.

AgentSession

  • Class/Interface
  • Classes
  • Components
An object that represents a single conversation instance, keeping track of the room state and history while running the voice pipeline.
5 other definitions

AgentSession · Components

An object that represents a single voice conversation session and manages the chosen audio pipeline providers.

AgentSession · Class/Interface

An object that manages the state of a conversation, including audio pipelines and history, for one user session.

AgentSession · Classes

An object that represents a single voice conversation session and coordinates the chosen speech and AI components.

AgentSession · Classes

An object that manages a single voice interaction, handling audio routing and tool calls for the agent.

AgentSession · Components

An object that holds the state of a voice conversation, including history and active audio pipelines.

Aggregator

  • Workflows
A module that combines many bundles back into a single one.

AI Act

  • Regulations
  • Core
The European Union's law on artificial intelligence. It sorts AI uses by risk, bans a few, sets duties for high-risk systems and requires transparency, such as labelling AI-generated content.

Also known as: EU AI Act, European AI Act

1 other definition

AI Act · Regulations

A proposed EU regulation that will set safety and transparency standards for AI systems.

AI agent (Onyx)

  • Concepts
A custom assistant you configure with its own instructions, a scoped set of knowledge (connectors), and actions it may take — e.g. a 'policy' agent that answers only from the HR handbook and cites the clause.

AI Developer

  • Features
A feature that converts a design brief into ready‑to‑copy HTML, CSS (and optionally JavaScript) code for a website.

AI Docs

  • Features
A tool that expands an outline prompt into a multi‑section long‑form document with headings and paragraphs.

AI layer

  • Concepts
The version-controlled context that teaches the agent your codebase — rules, commands and skills — kept next to the code.

AI literacy

  • Core
The knowledge a person needs to use AI tools sensibly: what they can do, where they fail and which rules apply. The EU AI Act requires organisations to make sure staff who work with AI have enough of it.

AI Sheet

  • Features
An assistant that turns plain English instructions into tables, formulas and charts inside a spreadsheet.

AI Slides (Guide Mode)

  • Features
A mode in the AI Slides app that asks you about audience, style and length before automatically building a presentation deck.

AI Studio

  • Interface
The main editing workspace where you adjust script, captions, background and avatar settings.

ambient mode

  • Concepts
A background process that periodically re‑indexes stored vectors and removes low‑relevance entries to keep memory fresh.

Annotation

  • Features
A hand-curated question-and-answer pair you save in Dify so the app returns your exact pre-written response whenever a sufficiently similar question appears, bypassing the LLM entirely.

anonymisation

  • Core
Removing or changing personal details so that nobody can identify the person again, even with other information. Truly anonymous data falls outside the GDPR, but it is harder to achieve than it looks.

Also known as: anonymised data, anonymization, anonymous data

Answer Engine

  • Concepts
What Perplexity calls itself — instead of returning a list of links like a search engine, it reads the web in real time and writes a direct answer with cited sources.

anthropic/claude-fable-5

  • Models
An OpenRouter model ID for Anthropic's Claude Fable 5, a high-capability model designed for long-running, autonomous coding and knowledge-work tasks.

Antigravity

  • Concepts
Google's standalone desktop application for AI-assisted software development, where one or more AI agents autonomously plan, write, and test code on your behalf.

Antigravity CLI

  • Concepts
A command-line version of Antigravity that lets you run agents directly from your terminal without opening the desktop app.

Antigravity SDK

  • Concepts
A set of developer tools that lets you embed Antigravity's agent capabilities inside your own programs or infrastructure.

Apache 2.0 licence

  • Core
A permissive open-source licence that allows use, changes and commercial use, and also grants patent rights. You must keep the licence text and note any changes you make.

Also known as: Apache License 2.0, Apache 2.0, Apache 2.0 license

API

  • Core
Application programming interface: a defined way for one program to talk to another, for example to send a prompt to a model and get the answer back. Tools use APIs behind the scenes; to call one yourself you usually need an API key.

Also known as: application programming interface, APIs

API key

  • Concepts
  • General
  • Core
A secret code that identifies you to a service's API and lets programs use it on your account. Anyone who has the key can spend your money, so keep it out of documents, chats and code.

Also known as: API Key, API token

4 other definitions

API key · Concepts

A secret code you copy from Cartesia that lets other programs prove they are allowed to use Cartesia’s voice service.

API key · General

A secret string that proves you are allowed to call Deepgram’s services.

API Key · Concepts

A secret credential you enter in Dify when connecting a model provider or external service — it authenticates your workspace so the service accepts requests from your application.

API key · Concepts

A secret token you paste into JCode after /login so it can call an external AI service on your behalf.

api_key

  • Concepts
  • Files & config
  • Libraries & Code
A secret password-like string you get from an AI provider's dashboard; you pass it when connecting so the service knows who you are and can bill you correctly.
4 other definitions

api_key · Files & config

The credential, created in the Groq console, that authorises your requests; passed to the client so your script can call the API.

api_key · Concepts

A string you set in Jan's API server configuration that callers must include in requests; Jan accepts any string you choose, and you can also leave it empty to disable authentication entirely.

api_key · Libraries & Code

A configuration field where you provide a password or token to authenticate with an API; LM Studio does not require a real key by default, but the field must still be present (any placeholder string works).

api_key · Concepts

A secret string that identifies who is making an API request; when using Ollama locally no real key is needed, but the library requires the field to exist.

App Visibility

  • Features
A dashboard setting that controls who can reach your published app: public to anyone, your workspace, or private/invited users only.

Apple Silicon

  • Concepts
The ARM‑based processor family used in newer Macs.

apt-get

  • Commands
A command‑line tool used on Debian‑based Linux to install, remove, or manage software packages.

argparse

  • Concepts
A built-in Python module that lets your script accept named options (like --input or --threshold) typed on the command line, so you don't have to hard-code values inside the file.

ARM64

  • Concepts
Another name for the 64‑bit ARM architecture used by Apple Silicon.

Artifact

  • Concepts
A document, diagram, chart, or runnable code snippet that Claude generates in a side panel where you can refine, copy, download, or share it.

Artifacts

  • Concepts
Structured outputs an agent produces — such as task lists, implementation plans, code diffs, screenshots, and walkthroughs — so you can review what it did before accepting the changes.

Also known as: artifacts

1 other definition

artifacts · Concepts

Everything the agent produced or touched in a session — files, links, images — your record of what it did.

artificial intelligence

  • Core
Software that does tasks we used to think needed human judgement, such as writing text, recognising images or answering questions. In this curriculum, AI mostly means large language models and the tools built on them.

Also known as: AI

aspect ratio

  • Parameters
The width‑to‑height proportion of the generated picture or video, like 16:9.

Assignee

  • Interface
The person selected to work on an issue, shown by their avatar on the issue card.

Assistant

  • Concepts
The most beginner-friendly Flowise builder, which lets you create an AI agent that follows instructions, uses tools, and retrieves answers from uploaded files — without wiring individual nodes.

async

  • General
A way of writing code that can pause while waiting for data (like audio chunks) without stopping the whole program.