Most chat bots help users do one or two discrete things. A bank chat bot may help you manage your account. A hotel chat bot may help you book a room or answer questions during your stay. These are very useful, but what if we could build a chat bot that guided the user through their whole journey with you?

For example, what if a hotel chat bot could not only help you with booking the room, but could follow you throughout your stay with the hotel? …

How can we build a virtual assistant that makes a real difference to businesses by improving customer satisfaction and reducing costs?

What makes a virtual assistant suitable for businesses? These assistants need to better understand what is being asked and engage in multi-turn conversations as well as digressing to other topics. This is somewhat different to the usual one-turn conversations to get weather forecasts or tell jokes. They can also be integrated into backend systems to retrieve data or invoke actions.

So how does Watson Assistant help you to build assistants for business? …

IBM Watson Assistant has recently introduced a new feature called Contextual Entities, and we are going to build a simple bot to show it in action. If you are not familiar with Watson Assistant you may want to read Getting Chatty with IBM Watson first.

Entities are used for identifying interesting parts of the user’s utterance, such as names and dates. Watson Assistant already provides system entities (for date, time, names, etc), and lets you define entities with synonyms and fuzzy matching, as well as defining pattern-based entities.

Now you can define entities based on their context in the utterance…

A good way to learn how to build a bot in Watson Assistant (formerly Conversation) is to see an example of how a bot is built. So I thought it would be useful to walk through the details of an example bot. If you are not familiar with the basics then it may be worth reading Getting Chatty with IBM Watson first.

The example we will be using is a restaurant bot. It answers various questions about a restaurant and can book a table. …

This article describes a new feature in Watson Assistant (formerly known as Watson Conversation), called “Digressions”. If you are not familiar with building a dialog you may want to read “Getting Chatty with IBM Watson” first.

Normally in a conversation when you have gone down a particular flow in the dialog and the user says something that is not handled, the dialog falls back to the root level and tries to answer from there. Now, that point in the flow has been lost. With “Digressions” you are able to return to that point in the flow.

Do you remember the IBM Watson advert with Bob Dylan from a while back? I thought it would be an interesting project to actually try to build something like that.

It’s also a fun way to show how to build a conversational analysis solution, that is creating a corpus of unstructured data and then interactively querying it in a conversational way.

To make this even more interesting (for me at least) I decided to analyze the lyrics of my favorite artist, Prince. …

For my latest little side project, I decided to do something a bit more experimental…the world’s first cognitive writing game! Try it at

The aim of the game is to write a story following certain steps and emotions. So the game tells you the next step in the story that it expects, as well as what sentiment and emotion it wants by the time you reach that step. The idea is not to immediately write the next step, the player must build up to the step by setting the emotion and sentiment.

Understanding the writing

To understand what is being written I…

Chatbot Design Tutorial

Conversational Design is a new area of design which has come about due to the rise of chatbots. Just as User Experience (UX) design is important in building a great traditional interface, Conversational Design is important for creating great chatbots. Of course there are similarities to regular UX design, but there are also aspects which are specific to conversational interfaces.

If you’ve already built a chatbot without taking the time to really design it, it’s well worth going back and designing the tasks you have already implemented to improve the experience and create a better base for additional tasks.


Recently we had another hackday in the Watson team at IBM (see our last hackday project “A Cognitive Mystery”). This time we decided to design and build a solution that would enable using Watson Assistant as a guide. Now this could be a guide for almost anything, e.g. cooking, tutorials, tour guide, etc. We decided to build a tutorial bot for the Assistant itself, i.e. we would use Watson Assistant to build a tutorial bot to help people get started with Watson Assistant.

The benefits of doing a tutorial in this way are:

  1. You are proactively being prompted to take…

If you want to get in on the bot action, here’s a simple way to do it. Check out Burger Bot, which is all about your fast food experience. However, for us this is a really simple bot just to show you how things work.

There are three main parts to it:

  • The front-end, which runs in your browser, and allows you to enter messages.
  • The back-end which exposes an API for the front-end to call, and which communicates with…
  • The Watson Assistant service, which runs in the IBM cloud.

The front-end and back-end are included in the github project

Simon Burns

User Experience Developer | IBM Watson

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store