> For the complete documentation index, see [llms.txt](https://docs-en.yoctol.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs-en.yoctol.ai/term-translations/utterance.md).

# Utterance

**Utterances** are various ways of expressions for the same [intent](https://app.gitbook.com/@docs-en-yoctol-ai/s/yoctol/~/edit/drafts/-LnQJsTXatUDJ-slOjKr/v/master/term-translations/intent) used by the chatbot to learn and categorize the intent.

We recommend a number of 3-5 utterances for each intent with diverse and representative sentence structures. Each intent has a maximum of 30 utterances.

You can utilize [“entities”](https://app.gitbook.com/@docs-en-yoctol-ai/s/yoctol/~/edit/drafts/-LnQJsTXatUDJ-slOjKr/v/master/term-translations/entity) and put various utterances with similar sentence structure in one utterance only. Each utterance can have a maximum of 3 entity values.

### Example

Take a beverage shop chatbot as an example. If we want to train it to understand the intent of delivery request, the following would be possible utterances for this intent. In utterance 3, we can use an entity of “drink name” instead of using countless\
utterances to list out all the drinks. If there are entities used, you can use the symbols {{ }} to mark them.

1. I want to order many cups!
2. How many cups do I need to buy for delivery?
3. How long will it take to deliver 10 cups of {{drink name}}
4. …


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs-en.yoctol.ai/term-translations/utterance.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.