# Instinct-AI

Instinct AI is the brain of the Chatman. You can train your bot by adding intents as per the user utterances and crafting replies accordingly. When the visitor engages with specific intent, Instinct AI reverts with an automated reply as a text message, journey, or block based on set conditions.

In simple words, the Instinct AI decides how your bot will respond to customer queries.  The better you understand, the better your bot responds, elevating the customer experience.          

Training the Chatman bot is the easiest when compared to other bots in the market. However, you need to understand the concept well. Chatman has only four major terms, understanding which you train it to respond to user queries with accuracy. Let's understand these in greater detail!

### Terms Related To Instinct AI

<details>

<summary>Intent</summary>

An intent represents the purpose or goal of a user's message. If a user says "Order pizza," the intent is to place a pizza order.

</details>

<details>

<summary>Utterances</summary>

Utterances are examples of how users might express a particular intent. For the "Order pizza" intent, utterances could include "I want to order a pizza" or "Can I get a pizza, please?"

</details>

<details>

<summary>Catch All</summary>

A default intent used when the bot cannot determine the user's intent. If a user sends a message that the bot doesn't understand, it can respond with a fallback message like "I'm sorry, I didn't catch that."

</details>

<details>

<summary>Triggered</summary>

In Instinct AI, this means how many times a particular intent has been sent by customer.

</details>

Now that we know the terms, let's see the primary options in Instinct AI.

### Train Your Bot

Add frequently asked user queries as intents and formulate corresponding replies.

{% content-ref url="/pages/wmX91kRg7b83AbR8w5HE" %}
[Train To Bot](/chatman-enterprise-whatsapp-platform/chatman-functions/instinct-ai/train-to-bot.md)
{% endcontent-ref %}

### Intents

Check all the intents your created in train to bot.

{% content-ref url="/pages/2lOuJcBwvNhlds4xFZE0" %}
[Intents](/chatman-enterprise-whatsapp-platform/chatman-functions/instinct-ai/intents.md)
{% endcontent-ref %}

### Catch-All

Formulate a response for the user utterance that could not be understood by the bot.

{% content-ref url="/pages/1kb79BEjqQtTrUByL2Jo" %}
[Catch All](/chatman-enterprise-whatsapp-platform/chatman-functions/instinct-ai/catch-all.md)
{% endcontent-ref %}

### Summary Report Of all Intents

Find how your intents are performing and how can you make it better.

{% content-ref url="/pages/QVU50ps5jgDu5bBqsoqK" %}
[Summary](/chatman-enterprise-whatsapp-platform/chatman-functions/instinct-ai/summary.md)
{% endcontent-ref %}


---

# 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://docs.makerobos.com/chatman-enterprise-whatsapp-platform/chatman-functions/instinct-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.