# Summary

Here, you will obtain a deep understanding of the intents asked, helping you know the interests and problems that visitors/customers face with your business, and accordingly, you can draft a specific message or journey for the same.

<figure><img src="/files/uv1ugirWqoktq0Ea7q8X" alt=""><figcaption></figcaption></figure>

### Key Points  In Summary

#### Intent

Intents are the names/queries that you want the bot to understand. Under intent, you can see a list of intent names and, besides that, their performance. Knowing the accuracy and effectiveness of intents is crucial for assessing the bot's overall performance.&#x20;

#### Messages

Messages tell you about the frequency, i.e., how many times a particular intent has been sent by a bot. Knowing the frequency, tells about regular intents, and you can train the bot accordingly to respond back with a better reply.

#### Importance

Assigning appropriate importance levels to intents ensures that the bot prioritizes and handles critical tasks effectively.&#x20;

#### Accuracy

High intent accuracy is a key indicator of a well-trained bot. Regularly assessing and improving accuracy helps in refining the bot's natural language understanding, reducing errors, and enhancing the overall user experience.&#x20;

#### Catch-All

Analyzing the catch-all performance aware of how effective the catch-all mechanism is and hence tells about user interactions. It helps to know the situations where the bot might not have a specific intent defined for a particular user input.


---

# 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/summary.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.