In the Insights tab, we use Generative AI Agents to monitor all of your conversations based on a specific over-arching category. For example, "Customer Issues" or "Product Requests." Conversations within these categories will be grouped by theme and sub-theme, allowing users to quickly find out what is happening in their conversations, even if they weren't aware of a particular topic before.
A 'stream' is a collection of conversations that have been grouped based on a specific question or objective, such as understanding customer intent or collecting information about a product. The underlying technology involves the use of AI Agents; however, it might be more intuitive to consider each stream akin to a human analyst, who has been given specific instructions for what to look for in your customer conversations.
Imagine an expert whose primary role is to sift through all of your conversations, applying a specialized lens to each interaction.
Understanding Themes and Reflections
Themes are a high-level grouping of conversations. You can click on them to see a description of the sort of conversations in the group. You will also see a list of more granular groupings of conversations called 'reflections'. These can be thought of as "sub-themes".
Each reflection or sub-theme in the list will also come with a description as well as a count of the number of conversations it represents.
When you click on the Discover icon, it will take you to the Discover page and see all the conversations that map on the selected reflection.
Using the "Error message when logging in" reflection as an illustration, the Discover page will display all conversations that are mapped to this particular issue.
We hope this was helpful! Please submit a ticket here if you have any questions or need further assistance.