Assemble a pizza-ordering chatbot dialog  

Easily create a complex dialog with Watson Assistant Slots, Node.js, and IBM Cloud Kubernetes Service

Last updated | By Scott D’Angelo


If you’ve used Watson Assistant and needed to have the user input data, you’ve noticed that the process can be cumbersome. Each time you added a field required a node, and validating the required logic was done on another node. Error handling, adding help, optional fields, and other logic would require even more nodes. Just creating a user profile or data form resulted in a large graph and extensive application logic. With the new Watson Assistant Slots feature, you can reduce that down to a single node. This code pattern shows how to create an online pizza order for a chatbot using a single node for input. After implementing this code, you will have the knowledge to create your own Watson Assistant Slots. This code pattern now includes instructions on how to use the IBM Cloud Kubernetes Service, too!


In this code pattern, we’ll create a simple chatbot with Node.js and Watson Assistant. There will be only a thin application layer, which provides the bare bones of a basic chatbot, with all the logic pushed into Watson Assistant via the new Watson Assistant Slots feature. The chatbot will take a pizza order, filling in slots for the various information required. A similar approach could be used for a user profile or other online form.

When you complete this code pattern, you will be able to:

  • Create a simple chatbot using Node.js and Watson Assistant
  • Use Watson Assistant Slots to fill out required data
  • Use slots handlers to handle conversation flow that does not fit into slots

The code pattern lets you also choose how to deploy the application, using Cloud Foundry on IBM Cloud, or the IBM Cloud Kubernetes Service.


  1. User sends dialog to cloud-based Node.js application.
  2. Application interacts with Watson Assistant and uses slots.
  3. Replies from Watson Assistant are returned to user via application.

Related Blogs

Two “edgy” AI TensorFlow models for you!

The global Call for Code is well underway, we want to share some visual recognition models which could help you. These AI models can operate on the edge, which could be particularly useful for this years’ theme: disaster preparedness. How could visual recognition help in relief work? From satellite and drone imagery analysis, to classifying...

Continue reading Two “edgy” AI TensorFlow models for you!

Leveraging the power of AI at Unite Berlin

Last week, from June 19 – 21, we were at Unity’s premiere in Berlin: Unite 2018. This conference brought together Unity’s video game and development community. Unity touches 770 million gamers all over the world and is the market leader for consumer AR and VR use cases and is also rapidly emerging as the market...

Continue reading Leveraging the power of AI at Unite Berlin

Related Links

Building a dialog

Watson Assistant documentation details how to build a dialog, including the use of slots.