# AI

The AI endpoint can be used to train the Xenioo AI engine with new utterances for an intent. The utterance supplied will be added to the list of utterances for the intent and, if the bot is already published, it will become immediately part of the online training.

### Request

The following request will add a new utterance to an intent:

```bash
curl --location --request POST 'https://<NODE>.xenioo.com/ai/train' \
--header 'Authorization: Bearer <BOT_AUTH_TOKEN>' \
--header 'Content-Type: application/json' \
--data-raw '{
	"IntentKey":"<INTENT KEY>",
	"Utterance":"<UTTERANCE TEXT>"
}'
```

### Response

No data response is expected from this endpoint.&#x20;

### Response Codes

This endpoint will reply with the following standard HTTP codes.

| Code | Meaning                                                                   |
| ---- | ------------------------------------------------------------------------- |
| 200  | Ok. The request has been successfully fulfilled.                          |
| 400  | Bad Request. The call does not contain the data required to be fulfilled. |
| 404  | Not Found. The specified intent or chatbot have not been found.           |
| 302  | Found. An utterance similar to the one supplied has been found.           |


---

# Agent Instructions: 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://docs10.xenioo.com/xenioo-api/globa-platform-api/ai.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.
