If you’ve used Siri, Alexa, or Google Assistant, you’re already familiar with how Chatbot works. It is a program that allows you to interact with your computer by talking to it. At least he’s trying to talk to you. Historically, chatbots have been pretty clunky and not all that useful.
Now everything has changed significantly. We use voice assistants all the time, and they almost always know what we mean. Log into just about any commercial site, and the little messaging app that comes up probably doesn’t have a real person offering you help.
Chatbots are revolutionizing the way we use computers, but modern chatbots are difficult to program and time consuming to learn. This is why we now have many companies offering chatbot builders to (relatively) simplify this process.
IBM, the leader in artificial intelligence technology that powers the world’s best chatbots, offers a chatbot creation tool that you can try for free. It’s called IBM Watson Assistant and allows anyone to use one of the most advanced artificial intelligence systems in existence.
You may have heard of Watson before, especially when he defeated human opponents in Jeopardy! It’s not just a toy, you can build a viable chatbot using their technology and then integrate it into your business. or personal use cases.
A free account allows you to make up to 10,000 API calls to Watson Assistant .per month. For most personal users, this will be more than enough. Of course, that’s enough for what we’re going to do here!
Divide it into essentials
Before we get into the basics of building a chatbot with Watson Assistant, let’s talk about what we want to achieve.
The main purpose of a chatbot is to interpret what the user is saying and then figure out what to do about it. Watson Assistant .has something called an intent , which is essentially an action that the user wants to take.
For example, someone wants to know if you have a specific item in stock. In this case, Watson Assistant .can be integrated with your database and then get accurate inventory levels from there.
The intent is for objects that contain relevant information that Watson will use to respond.
When you create your chatbot, you follow a three-step cycle:
- Create intents and entities
- Create a dialog tree
- Put your chatbot to the test!
In this tutorial, we’ll go through one iteration of this loop to show you the basic building block of the Watson chatbot.
The first thing you need to do is go to the Watson Assistant . page and register. We have used the free “Lite” package, which allows you to create any chatbot without any obligation. Just click “Start Free” and follow the instructions.
Now click “Create”.
Now, just name your workspace and add a description.
Before we add our own intent, the first thing you need to do is add a few generic intents that IBM has already prepared for us. This saves you the trouble of teaching your bot the basics of conversation from scratch every time.
To do this, under Intentions, click Content Directory , and then click Add to Stage next to the General category.
The bot can now understand general dialogue such as greetings. To see how this works, click the Dialogue tab and click Create Dialogue. Two conversation nodes will be automatically generated – “Welcome” and “Everything Else”.
Click “Welcome” to expand it.
Here you can see the basic structure of the dialog node. If the bot recognizes a certain condition (for example, intent), it will react as you define.
While we didn’t create a specific intent in this case, let’s go to the Intentions tab and look at an intent called #General_Greetings. Just click #General_Greetings in the intent list to open it.
This is exactly how you should make your own intention. Give it a name, give it a description, and add as many ways as you can think of so the user can indicate that intent. Here IBM has already done all the work for us, but it’s clear how it works. You can also change this existing intent by adding more examples. Perhaps in your local dialect.
We’re going to use this intent as part of our chatbot dialog, so go back to the dialog tab and click Create Dialog. Our custom dialog will take place between the Welcome and Anything else nodes. All you have to do is click on Add Node.
We’re going to call this node Friendly Greetings and use the #General_Greetings intent to enable it. So under “If the bot recognizes” just enter the intent name and select it from the drop-down menu.
Now we leave our response as “text” and write what we want the bot to say in response to our greeting.
You can close the dialog by pressing the X button. We should now have a bot that can respond to a simple greeting. Click the “Try” button in the upper right corner of the page to test the bot we created. Enter “Hello” in the chat panel that appears and see what happens.
Wow! Watson realizes that we want to greet him, and then uses the rules specified in the dialog builder to respond. Congratulations, you’ve just gone through one complete chatbot creation cycle!
While you can build a pretty awesome chatbot using this basic loop of steps, Watson Assistant .is of course much more than that. Using all the capabilities of this tool, you can create a bot that will take care of the booking or present the user with a list of products that are in stock.
There is no limit to the possibilities and you don’t need to be a high-tech genius to get started. IBM has a variety of tutorial videos and documents to help you become a chatbot master. Now that you’ve tried it, nothing should be holding you back!