Glossary
Definitions of terms used in the curriculum.
Showing 801–840 of 902 terms in the glossary
Letter S16 terms
Storyboard
- Tools
- A feature that chains multiple short prompts together to create a continuous multi‑scene video sequence.
Storyboard feature
- Features
- An option that lets you chain several short prompts together in sequence, producing a longer narrative made of multiple AI‑generated clips.
1 other definition
Storyboard feature · Features
A function that lets you chain several short prompts together to create a longer, continuous video sequence. streaming
- Features
- A mode where the model sends its answer word-by-word as it is generated, so you can display text to the user progressively instead of waiting for the full response.
Also known as: Streaming
1 other definition
Streaming · Features
A mode where the AI sends its reply token-by-token in real time as it is generated, rather than waiting until the full response is complete before showing anything. structured output schema
- Settings
- A defined list of fields (e.g., Sentiment, Category) that tells the AI to return data in a predictable format instead of free text.
structured outputs
- Features
- A feature that forces the model's response to match a JSON schema you define, so your code always receives data in a predictable, machine-readable shape.
Style Exaggeration slider
- Settings
- A control that tells the model how strongly to emphasize the chosen speaking style, from subtle to extreme.
Sub-workflow
- Features
- A separate workflow that another workflow calls like a reusable function, helping you keep complex automations organised and avoid repeating the same steps.
subagent
- Concepts
- A helper agent with its own isolated context, used to parallelise or isolate work without contaminating the main session.
2 other definitions
subagent · Concepts
A specialist agent that a primary agent can invoke automatically to handle a subtask (like researching external docs); you can also invoke one manually by typing @agentname in your message.subagent · Concepts
A helper agent that runs in its own isolated context, so noisy or parallel work does not crowd your main conversation; it returns just a summary. Subagents
- Concepts
- Temporary, read-only helper agents Lovable spins up to research, inspect code, and browse the web in parallel before the main agent makes changes.
subprocessor
- Core
- Another company that a service provider uses to handle your data, for example the cloud host behind an AI app. Providers publish a list of their subprocessors, so you can see where your data goes.
Also known as: sub-processor, subprocessors
Super Agent
- Features
- A GenSpark feature that takes one natural‑language question and returns a brief overview with pros/cons and an action plan.
SVG
- File Types
- A file format for vector graphics that can be scaled without losing quality.
System Prompt
- Concepts
- Core
- Standing instructions that an app sends to the model before your own message, for example the role to play or rules to follow. You usually don't see it, but it shapes every answer.
Also known as: system prompt, system message
2 other definitions
System Prompt · Concepts
Hidden instructions you write once that shape how the AI behaves in every conversation — setting its persona, tone, and rules before any user message arrives.system prompt · Concepts
The instruction text that tells the AI what role to play and how to behave for all messages in a chat. systemctl edit ollama.service
- Commands
- Opens the Linux service configuration for Ollama so you can add environment variables (such as OLLAMA_HOST) that apply every time the server starts.
systemctl enable
- Commands
- A command that registers a service to start automatically each time the system boots.
Letter T24 terms
Tab
- Concepts
- Cursor's line-by-line code suggestion that appears as you type; press Tab to accept it or keep typing to ignore it.
Tables
- Data
- Zapier's built-in database for storing and reading data inside your automations.
Task
- Billing
- One action that completes successfully. Zapier bills by tasks, so each action that runs counts.
Tasks mode
- Concepts
- The part of the Claude Desktop app where you hand Claude a whole job to complete autonomously, instead of chatting one turn at a time.
tasks.yaml
- Files & config
- A CrewAI configuration file (in YAML format) where you describe each task — what it asks for, what output it expects, and which agent handles it.
temperature
- Settings
- Core
- A setting that controls how much randomness goes into a model's answer. Low values give steadier, more repeatable answers; high values give more varied ones, and some models don't let you change it at all.
Also known as: creativity setting
1 other definition
temperature · Settings
A setting that controls how creative or predictable the AI’s answers are; lower values make responses more deterministic. Template
- Features
- A pre-built workflow shared by the n8n community that you can import and adapt instead of building from scratch.
Templates
- Features
- Published v0 chats you can fork as a starting point, giving you a working app structure to customise instead of starting from a blank prompt.
terminal
- Core
- The window where you type commands for your computer instead of clicking. On macOS it is the Terminal app; on Windows it is usually PowerShell or Windows Terminal.
Also known as: terminal window, console
text to speech
- Core
- Turning written text into spoken audio with a computer voice. Modern voices sound natural, and some can copy a real person's voice, which needs that person's consent.
Also known as: text-to-speech, TTS, speech synthesis
Thinking Mode
- Interface
- A setting you enable so the AI knows it should do more complex work like generating a full presentation.
Thread
- Concepts
- A single conversation in Perplexity where each follow-up question keeps the context from previous turns, so you never have to repeat yourself.
Time to First Token
- Concepts
- How long you wait from sending your request until the very first word of the answer appears; shorter is better for real-time, interactive applications.
TLS
- Concepts
- Encryption protocol that secures data between the browser and the Open Notebook site.
token
- Concepts
- Core
- The small piece of text a model reads and writes, often part of a word. Providers count usage and prices in tokens, both for what you send (input) and for what the model writes back (output).
Also known as: input token, output token
3 other definitions
token · Concepts
A small chunk of text — roughly three-quarters of a word — that ChatGPT uses internally to read and generate language; token limits determine how long a conversation or document can be.token · Concepts
A small chunk of text (roughly a word or part of a word) that Gemini uses to measure how much it has read or generated; larger context windows allow more tokens.token · Concepts
A chunk of text (~¾ of a word) the model reads or writes; context limits are measured in tokens. tokens per second
- Concepts
- Size & speed
- A measure of how fast the AI generates text — one token is roughly one word or word-piece, so 3,000 tokens/second means about 2,000 words generated every second.
1 other definition
tokens per second · Size & speed
How fast a model generates text — higher feels snappier. It depends on both the model size and your hardware. Tone
- Features
- Overall style option—academic, casual, or debate—that shapes how the podcast sounds.
Tool
- Concepts
- Features
- A specific action an Agent or workflow node can call — such as searching the web, running a calculation, or querying an API — to get information or take action beyond text generation.
1 other definition
Tool · Features
A function that an agent can call to interact with the outside world, such as searching the web, running a calculation, or making an HTTP request. tool calling
- Features
- Core
- A model's ability to ask an app to run a tool, such as a search, a calculator or a database query, and then use the result in its answer. It is how chat assistants and agents act beyond writing text.
Also known as: function calling, tool use
1 other definition
tool calling · Features
A feature where you describe external functions (like a search engine or calculator) to the model, and it can request that your code run one of them mid-conversation to gather information. tool schema
- Data Formats
- A JSON description that defines what a custom function does, its required inputs, and how the model should call it.
1 other definition
tool schema · Data Formats
A JSON description that tells the model what a custom function does, what inputs it needs, and how to call it. Traefik
- Tools
- A reverse‑proxy router that directs web traffic to your containers and can obtain HTTPS certificates automatically.
training
- Core
- The process in which a model learns patterns from a large collection of examples. When a provider says it may use your chats for training, your text can end up shaping future versions of its model.
Also known as: model training, training data
transcription
- Core
- Turning spoken audio into written text. Check names, numbers and technical terms, which transcription gets wrong most often.
Also known as: speech to text, speech-to-text, STT
Translate (in export)
- Features
- A one‑click option that creates separate video files with dubbed audio and subtitles in chosen languages.