# Chat API

Our Chat API allows a user to have a conversation with your AI agent via a simple API call. 

The **messages** array should contain the conversation between the user and the AI agent. You can send the entire conversation within the API request. 

Each message object has a **role** (user or assistant) and **content**. 

In the example below you can see a short conversation between a user and an AI agent. 

The message from the user has the **role: user** and all replies from the My AskAI have the **role: assistant**.

{% openapi src="<https://content.gitbook.com/content/hu0WRsaCQQRKP3KeuIOQ/blobs/BfcMHrCjypJvVnFki8RA/chat.yaml>" path="/ask-ai-chat" method="post" expanded="true" %}
[chat.yaml](https://content.gitbook.com/content/hu0WRsaCQQRKP3KeuIOQ/blobs/BfcMHrCjypJvVnFki8RA/chat.yaml)
{% endopenapi %}

{% hint style="warning" %}
If your AI agent doesn't know the answer, the API will also return an additional field to confirm an answer wasn't found as well as 3 suggested questions the user can retry (these have a very high likelihood of being answered correctly):&#x20;

`"unknown_answer": "yes",`

`"suggestedQuestions": ["Example question", ...]`
{% endhint %}

{% hint style="info" %}
You can also pass in `"insights": true` to generate insights in your Dashboard from any API usage.&#x20;

When Insights is enabled in the API a `conversation_id` is also returned with each request. This can be included in subsequent API requests to keep the requests link to 1 conversation. However, you still need to always pass in the message history as the API is stateless.
{% endhint %}

{% hint style="info" %}
If human handover [guidance](https://support.myaskai.com/features/improve/guidance) is triggered the API response will include: `"human_handover": true`
{% endhint %}


---

# 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://support.myaskai.com/api-documentation/chat-api.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.