Today’s chatbot explainer post describes one of the most common node types encountered in the chatbot development process–Message Nodes. Message Nodes are classified in the Building category of chatbot product features, and they enable the chatbot to deliver one or more pieces of information to the customer. There are two main types of Message Nodes–Say Nodes and Question Nodes.

Say Nodes are used to deliver textual or multimedia messages to the customer. More specifically, the output types can include text, text with buttons, text lists, images, image galleries with buttons, audios, and videos. These different output types can be displayed across a variety of deployment channels such as webchat, Facebook Messenger, LINE, Microsoft Teams, voice gateway, and others. In addition, the enterprise user can also customize the output of the Say Nodes using JSON and SSML.

Question Nodes, on the other hand, are used to ask the customer questions in order to extract information from them. They can accept answers from customers in various formats including text, yes/no, intents, entities, dates, numbers, currencies, emails, and others. The format of the customer’s answer is compared to the format expected from the Question Node and if a mismatch is found, the node will reprompt the customer to input an answer in the correct format. The enterprise user can customize the reprompt message, and configure when the question should be skipped or escalated to a human agent if wrong answers have been given multiple times.

The screenshot above shows the editing of a Question Node in an example chatbot vendor – Cognigy.

Our chatbot explainer series shares our knowledge of chatbot product features. If you have any questions, please reach out to me directly and follow me to get notifications on future posts.

Dong Liu, Founding Analyst
dong@daybreakinsights.com

@dongliu1226