The Conversations tab provides insights into the interactions between your bot and the users, allowing you to assess the effectiveness and quality of those conversations.

Not familiar with analytics? We recommend that you have a look at our Analytics concepts.


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 action.

  • An average of the number of messages per conversation.

  • An average of the conversation duration. This category represents the most occurring length of a conversation in number of minutes for interactions between your bot and its users

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.

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: this shows how often users clicked on a button, carousel, quick reply etc.

  • Not understood: the user expression is not understood, meaning it is below the NLP threshold, so the user saw the Not understood message.

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. Creating better Not understood messages will also create a better user experience.

Knowledge base AI

The Knowledge base AI tab displays analytics on the usage of your Knowledge base AI flow if you've implemented one in your chatbot.

Chatlayer's AI knowledge base tool allows your bot to generate concise answers after scraping your content. Learn how to set it up here.

Last updated