> ## Documentation Index
> Fetch the complete documentation index at: https://www.voiceflow.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# AI terms

> Model, token, context window, RAG, embedding, grounding and hallucination: general industry terms, defined exactly as these docs use them.

General industry terms, defined as they are used in these docs. They are not
Voiceflow-specific, and are here so a page can link to one rather than explain
it again. One section per term.

## Models

### Model

The language model generating a reply. Which one an agent uses is a
[behaviour](/docs/documentation/build/behaviour) setting, and the choice affects both quality and
credit cost.

**Also asked as:**
- which AI is behind the assistant
- pick between the available LLMs
- the AI engine behind the replies
- swap the model for a cheaper one

**Related:** [LLM](#llm) · [Default model](/docs/resources/glossary/build#default-model) · [Credits](/docs/resources/glossary/measure#credits)

**Documented in:** [Behaviour › Default model](/docs/documentation/build/behaviour#default-model)

### LLM

Large language model. Used interchangeably with *model* above.

**Also asked as:**
- the large language model term
- what is a large language model
- the LLM the agent runs on

**Related:** [Model](#model)

**Documented in:** [Behaviour › Default model](/docs/documentation/build/behaviour#default-model)

### Token

The unit a model reads and writes text in, roughly a word-piece. Usage and cost are measured in
tokens, which is why [analytics](/docs/documentation/measure/analytics) reports them.

**Also asked as:**
- what a token means for cost
- how text is counted by the model
- why is usage measured in tokens
- tokens versus words

**Related:** [Context window](#context-window) · [Credits](/docs/resources/glossary/measure#credits)

**Documented in:** [Analytics](/docs/documentation/measure/analytics)

### Context window

How much text a model can consider at once, counted in tokens. Everything the agent sends on a turn
competes for the same window.

**Also asked as:**
- how much the model can keep in mind at once
- why a long prompt crowds out the conversation
- the limit on how much the model can read at once
- running out of context

**Related:** [Token](#token) · [Memory](/docs/resources/glossary/build#memory)

**Documented in:** [Behaviour › Memory](/docs/documentation/build/behaviour#memory) · [Global prompt › Keep it short](/docs/documentation/build/global-prompt#keep-it-short)

### Temperature

How much randomness a model uses when choosing words. Lower is more repeatable, higher more varied.

**Also asked as:**
- make the assistant more predictable
- the creativity setting
- make replies less random
- the setting for more creative answers

**Related:** [Model](#model) · [Default model](/docs/resources/glossary/build#default-model)

**Documented in:** [Behaviour › Default model](/docs/documentation/build/behaviour#default-model) · [Playbooks › Model settings](/docs/documentation/build/playbooks#model-settings)

## Prompts

### Prompt

The text given to a model to produce a reply. In Voiceflow this is assembled from the global prompt,
the instructions, and the conversation so far.

**Also asked as:**
- what the model actually receives each turn
- everything the model is given before it answers
- the text sent to the AI each turn

**Related:** [System prompt](#system-prompt) · [Global prompt](/docs/resources/glossary/build#global-prompt)

**Documented in:** [Global prompt › What is the global prompt?](/docs/documentation/build/global-prompt#what-is-the-global-prompt)

### System prompt

The instruction layer a model treats as standing orders rather than user input. Voiceflow's
[global prompt](/docs/documentation/build/global-prompt) fills this role.

**Also asked as:**
- where the standing instructions go
- the system message in Voiceflow terms
- the instructions the model always follows
- the equivalent of a system message

**Related:** [Prompt](#prompt) · [Global prompt](/docs/resources/glossary/build#global-prompt)

**Documented in:** [Global prompt › What is the global prompt?](/docs/documentation/build/global-prompt#what-is-the-global-prompt)

### Tool calling

A model choosing to invoke a tool, with arguments, instead of replying in prose. What makes a
playbook agentic.

**Also asked as:**
- the model decides to use a tool on its own
- function calling
- the model decides to call an API by itself
- how the agent picks a tool

**Related:** [Playbook](/docs/resources/glossary/build#playbook) · [Tool](/docs/resources/glossary/build#tool)

**Documented in:** [Playbooks › Tools](/docs/documentation/build/playbooks#tools)

## Retrieval

### RAG

Retrieval-augmented generation. Fetching relevant documents and giving them to the model so the
answer is grounded in your content rather than the model's training. This is what the
[knowledge base](/docs/documentation/build/querying-the-knowledge-base) does.

**Also asked as:**
- answer from our documents instead of the model's memory
- retrieval before generation
- retrieval augmented generation in Voiceflow
- how the assistant uses our documents to answer

**Related:** [Knowledge base](/docs/resources/glossary/knowledge-and-data#knowledge-base) · [Grounding](#grounding) · [Embedding](#embedding)

**Documented in:** [Querying the knowledge base](/docs/documentation/build/querying-the-knowledge-base)

### Embedding

A numeric representation of a piece of text, used to find passages that mean something similar
rather than merely sharing words.

**Also asked as:**
- how the knowledge base finds similar passages
- semantic search under the hood
- vector representation of text for search
- why similar wording is found even without exact words

**Related:** [Chunk](#chunk) · [RAG](#rag)

**Documented in:** [Importing data sources › LLM chunking strategies](/docs/documentation/build/importing-data-sources#llm-chunking-strategies)

### Chunk

One passage a document is split into before it is embedded. Chunking decides what retrieval can
return.

**Also asked as:**
- the passage size the bot retrieves
- how documents get split up
- a passage of a document used in retrieval
- the piece of text the bot gets back

**Related:** [Chunking strategy](/docs/resources/glossary/knowledge-and-data#chunking-strategy) · [Chunk limit](/docs/resources/glossary/knowledge-and-data#chunk-limit)

**Documented in:** [Importing data sources › LLM chunking strategies](/docs/documentation/build/importing-data-sources#llm-chunking-strategies) · [Querying the knowledge base › Chunk limit](/docs/documentation/build/querying-the-knowledge-base#chunk-limit)

### Grounding

Constraining an answer to supplied source material, so the model reports rather than invents.

**Also asked as:**
- keep the assistant to the facts in our content
- stop answers drifting from the sources
- make the assistant stick to the source material
- answers based only on provided content

**Related:** [Hallucination](#hallucination) · [Preventing hallucination](/docs/resources/glossary/build#preventing-hallucination) · [RAG](#rag)

**Documented in:** [Global prompt › #Guardrails](/docs/documentation/build/global-prompt#%23guardrails) · [Querying the knowledge base](/docs/documentation/build/querying-the-knowledge-base)

### Hallucination

A fluent, confident answer that is not true. The reason grounding and evaluations matter.

**Also asked as:**
- the bot makes things up
- confident but wrong replies
- the assistant states something false with confidence
- made-up answers from the model

**Related:** [Grounding](#grounding) · [Preventing hallucination](/docs/resources/glossary/build#preventing-hallucination) · [Evaluation](/docs/resources/glossary/measure#evaluation)

**Documented in:** [Global prompt › #Guardrails](/docs/documentation/build/global-prompt#%23guardrails)

## Protocols

### MCP

Model Context Protocol. An open standard for exposing tools to a model, so the same tool works across
clients.

**Also asked as:**
- what MCP stands for
- the standard behind tool servers
- the Model Context Protocol explained
- the standard that lets tools work across AI clients

**Related:** [MCP server](/docs/resources/glossary/developer-surfaces#mcp-server) · [Voiceflow MCP server](/docs/resources/glossary/developer-surfaces#voiceflow-mcp-server) · [MCP tool](/docs/resources/glossary/developer-surfaces#mcp-tool)

**Documented in:** [Voiceflow MCP overview](/docs/mcp/overview) · [MCP tool](/docs/documentation/build/tools/mcp-tool)

<Note>
  Capitalisation carries meaning here. "Agent step" and "Function step" name
  specific steps; the bare words *step* and *tool* stay lowercase.
</Note>