> For the complete documentation index, see [llms.txt](https://docs.chatlayer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.chatlayer.ai/navigation/analytics/conversations.md).

# Conversations

{% hint style="info" %}
Not familiar with analytics? We recommend that you have a look at our [Analytics concepts](/bot-answers/definitions.md).
{% endhint %}

## Overview

The **Overview** tab is where the overall info on the conversations lies. It consists in:

* The total number of conversations.
* The number of conversations with human handover. A conversation is marked as a human handover when it includes a triggered [Offloading](/navigation/settings/offloading.md) action.
* An average of the number of messages per conversation.
* An average of the [conversation](https://docs.chatlayer.ai/bot-answers/definitions#definition-of-a-conversation) duration. This category represents the most occurring length of a conversation in number of minutes for interactions between your bot and its users

<figure><img src="/files/Ifa1GLYQaQnP9fsLw2Ql" alt=""><figcaption><p>Conversations Overview tab.</p></figcaption></figure>

{% hint style="success" %}
Monitor the efficiency of your conversations by looking at the average messages and duration per conversation to ensure quick user resolutions. An increase in these metrics indicates users are struggling. Compare with past effective performance, identify changes, and adjust the bot to enhance user experience.
{% endhint %}

## Customer messages

The **Customer messages** tab shows an overview of how many messages are:

* Understood: the user expression is recognized correctly and the corresponding intent was triggered.
* [Button clicks](https://docs.chatlayer.ai/bot-answers/analytics/intents): this shows how often users clicked on a button, carousel, quick reply etc.
* [Not understood](https://docs.chatlayer.ai/bot-answers/analytics/intents): the user expression is not understood, meaning it is below the NLP threshold, so the user saw the Not understood message.

<figure><img src="/files/BGxzSA9lpnmJinmDE8gs" alt=""><figcaption><p>Customer messages tab.</p></figcaption></figure>

{% hint style="info" %}
Seeing a 'not understood' percentage of > 15%? You should look into which intents are not understood correctly and improve your NLP by using the [Train tab](https://docs.chatlayer.ai/understanding-users/natural-language-processing-nlp/tutorial-train-your-bot-based-on-actual-user-messages). Creating better[ Not understood messages](https://docs.chatlayer.ai/tips-and-best-practices/not-understood-bot-dialog) will also create a better user experience.
{% endhint %}

## Knowledge base AI

The **Knowledge base AI** tab displays analytics on the usage of your [Knowledge base AI flow](/navigation/knowledge-base-ai.md) if you've implemented one in your chatbot.

<figure><img src="/files/JWNOWswNBZSNHvA6JwGb" alt=""><figcaption><p>The Knowledge base AI tab in Conversations.</p></figcaption></figure>

{% hint style="info" %}
Chatlayer's AI knowledge base tool allows your bot to generate concise answers after scraping your content. Learn how to set it up [here](https://docs.chatlayer.ai/bot-answers/knowledge-base-ai).
{% endhint %}


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.chatlayer.ai/navigation/analytics/conversations.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.