Like we said earlier, we're gonna build this chatbot in Node.js.

We definitely invite you to follow along with your programming language though.

As you'll see the Blue Mix documentation is great and

contains examples in Node, Java, and Python, which makes it easy for

you to do the same thing we're doing in a different language.

Now Armen and I are working on local Node installations using a text editor.

It's very easy to set up, so if you need to do that check out

the installation instructions we included in the teacher's notes.

It will walk you through setting up Node and NPM on a Mac, Windows or Linux.

And if you need a text editor, I'd recommend Atom from GitHub,

which is free and easy to use, and also linked below.

All right, so once you have Node set up on your local computer,

you can download the project starter files from the teacher's notes and

use them to follow along.

Now if you prefer to use Treehouse workspaces for this,

you can launch one using the button on this page.

It will load a workspace with the same project files we're going to use locally,

so you should be able to follow along directly.

The only issue is that currently we have a bug in how .env files are edited.

In workspaces you need to add .txt to the file name to make some changes and

then you have to remove that .txt extension and Save it and

then you can use it in the app itself.

We are essentially working through the steps outlined in this training guide

in the Watson Docs.

This link is in the teacher's notes and it would be helpful for

you to bookmark it to refer to later for review.

I've just created a brand new account, and I've confirmed it through email.

And now we're at this page where we need to create an organization.

So Armen, can you help me set this up correctly?

>> Gladly Ben.

A few steps that we want to pay attention to.

Notice the region that is selected for you happens to be US South.

We are going to keep that, that is the region we are closest to.

And we need to create an organization.

If below you can see there are two suggested names.

One of them is your email, and the other one is your shorter form of email.

I recommend picking the ones just right there as opposed to typing a new one,

whichever you'd like.

>> Sounds good.

>> Now we're going to create a space,

again, notice the suggestions down there, development, test, production.

Pick one of those.

>> Lets do dev.

Yeah, that makes sense.

Okay, it looks like we are set up with the basics.

Click here? >> Very well, yes.

>> And we are coming up on the dashboard.

All right mine does not have as much as yours did.

>> A good place to go typically at this time, Ben, is to click the Catalog tab.

And now, we have a great view of all the services that are on our platform.

>> Cool, yeah, like you mentioned before, more than just Watson,

there are a lot of other services available.

But I'm guessing I want to click Watson down here at the bottom of

the platform site.

>> For our purposes, let's go to the Watson set of cognitive services.

And let's just take a look at the 12 services that are here.

We'll be working with the Conversation service,

we'll also work with the Discovery service, and

another one of our favorites is the Tone Analyzer.

Interesting to note that the Natural Language Classifier, Ben,

is included in the Conversation service.

>> Right right.

>> That really helps in disambiguating and

taking care of the nuances of our speech, our colloquial way of speaking.

>> So that's the magic behind the scenes.

We're using the Conversation service, which is a wrapper for

all of the other work that Watson is doing for us.

>> Absolutely.

Another good point to note is that NLC,

that's your language classifier, is trained on Wikipedia.

So you're already getting machine learned set of

training data where, from there on, we can go on.

And it allows us to speak comfortably, colloquially,

and it would understand our nuances in our speech.

>> Very cool.

All right so, I should click on Conversation, right?

>> Yes, let's start with the Conversation service.

Wonderful, a good habit is to give the service a name,

typically I leave Conversation intact and just backspace over the 95 and

something meaningful to you, your name or whatnot.

This is our Ben and Armen together.

Here we go.

>> Wonderful, and really, that's all we need.

Let's click Create.

>> I see it's got organization and the dev space we created.

>> Absolutely.

>> Let it spin for a moment.

All right, looks like we have it.

>> Wonderful Ben, let's go ahead and

a few things I'd like to show you before we do click on the Launch tools.

Notice the Service credentials link to the left.

Let's explore that.

Further down, you're seeing View credentials to the bottom of the page.

>> This is gonna important shortly.

>> You're absolutely right, that username and

password is really our currency as we're dealing with RESTful services.

We will be copying pasting that in a number of files.

Very well back to the Manage, and let's click Launch tool.

>> Okay so it's asking me to login again, but hopeful it retains my credentials and

lets me through.

>> And it's true, yes.

Interesting to note that out

of the box you are presented with a Car Dashboard sample app.

>> Very helpful.

>> Very helpful, it allows us to get started with an already built Conversation

full of entities, intents, and so forth.

[COUGH] In early example we're going to create a new workspace.

>> Cool, and we'll come back to that sample later because we do wanna look at

some of the stuff in there.

But for the new one, what kind of name should I give this?

I guess this is a different car dashboard?

>> Correct. >> This is the Treehouse Car Chatbot.

And I can give it an optional description if I want,

working on the course with Armen, and Create.

>> Notice Ben, you are presented by a workspace.

A workspace is a container full of the artifacts that define

the conversation flow for an application.

The natural language processing for

the conversation service happens inside a workspace and you should add information.

The workspace trains itself, as we will note,

the automatic training of the system that takes place in the background.

You don't have to do anything to initiate it.

This will make more sense as we add different parts to it.

We should also note that a single Conversation

service instance can contain multiple workspaces.

Here is an example of why you may want to have more than one workspace.

Perhaps one of your workspaces is for chit-chat.

The greetings and the hello's and goodbye's,you can keep that separate from

the more germane and core topic of your conversation in a separate.

>> That's a good idea, I love well organized components like that, very cool.