Conversation Flow

Conversation Flows provide a visual representation of the user journeys and give insights into commonly used tasks, utterances that guided the conversations, preferred paths, and usage details.
You can also view the dropout rates at various stages of the conversation.

Note: Conversation Flow is available only for user interactions with the Published Bots.

To understand the complexity of an user interaction with a bot with an easy interface, this visual tool is being created and this can be understandable by a designer, developer and a tester.

This is more like a simple, visual interface to understand complex conversational flows between users and bots.

Understanding about the terms present in conversation flow,

In Conversational flow, Every flow starts with an utterance from the user that initiated the conversation and expands to show further interactions. These utterances are grouped based on similarity. ( ignoring the stop words and values for entities.)


In Simple terms,

1.Every flow starts with an utterance.
2.The utterance node leads to an intent (Individual task intents, FAQs, Small Talk, Help or Not Handles utterance).
3.Nodes (need input from the user are plotted on the graph). These could be Intent, Entity, confirmation, user input or message nodes).
4. The most important part of the graph is the Node Details. Which shows the details like
Percentage of total utterances leading to this Node. Click on percentage to display the list of user utterances that triggered this Node;
Node Name will be the the task/entity name with the following details displayed on hover over the Node:
Conversation and Drop-offs details, See Responses shows the User’s response, where applicable, to this Node;
5. Chat History can be seen on clicking the utterance from the User Utterance window for either input (percentage) or response information.

For example, this is the screenshot of the conversation flow for a sample bot which clearly shows the Drop offs which could be helpful in determining further Drop-offs details.


Filters can be used in Conversation Flows.

The Conversation Flows can be filtered using one or more. Few existing data filters are Date Period, Languages, Channels and Custom Tags.

For more understanding, please refer to