Train TJBot to Converse in Node-RED

Today we’ll train TJBot to respond to natural language with a simple response using the converse node and the Watson Conversation service.

TJBot can recognize natural language from the user using the IBM Watson’s Conversation service. Create a Watson Conversation service and copy the username and password credentials into the Conversation section.

The Watson Conversation service needs to be trained. Create a new workspace named TJBot, that will contain this training.

In the Watson Conversation tooling, you can create intents and entities, and use them in the dialog tooling, to process natural language and help TJBot understand what to do. For today’s skill, TJBot can greet the user or respond with a fallback message.

When this flow is run, you can see the response from the Watson Conversation API in the debug window.

Here’s a video of how to train TJBot to get the initial greeting from the Watson Conversation service.

That’s it for today’s skill. What can you train TJBot to do now that it can use Watson Conversation? Stay tuned for more training sessions that will use Watson Conversation in more depth.

Come back tomorrow and we’ll talk about connecting the analyze tone node and the shine node to analyze emotions.

This post is part of a series of skills you can train TJBot to perform.