Exploring New Tech with Starter Projects featuring Chalkers

Hi, I'm Craig. 0:00 Welcome to The Treehouse Show. 0:01 The Treehouse Show is our weekly conversation with the Treehouse community. 0:02 Have you ever had that feeling where you're ready to start using a language or 0:09 some new technology that you've just learned about, but 0:13 then you realize I don't know where to start. 0:15 Now this is a common enough problem that I thought I'd reach out to our resident 0:18 expert teacher Chalkers to get some advice. 0:22 Thanks for being on the show Chalkers. 0:24 >> It's good to be here. 0:26 >> I was thinking, that we could talk about a common problem that students have, 0:27 and that is the blank slate problem. 0:31 And by that I mean when you get to some technology. 0:34 You've gone through it a little bit. 0:38 You've gotten your hands a little bit wet with it. 0:39 You've done some exploring, but you go to start your own project and there is. 0:41 Now what do I do? 0:47 Now how do I start? 0:48 What do I even think about? 0:49 How do I use these tools that are in front of me? 0:51 What's your take on the blank slate problem? 0:54 >> My take on the problem is that you've just gotta start somewhere. 0:55 >> Okay. 0:59 >> And getting something working, 1:00 in a fashion, is probably the best solution. 1:04 So can you install this stuff on your machine, and 1:10 get it just running with a demo project? 1:12 >> Okay. 1:14 What do you mean by demo project? 1:17 >> So say for example a lot of these services out there, or 1:19 even frameworks normally have a hello world example project. 1:22 >> Okay. >> That you can just clone. 1:27 Some boiler plate code that you can just run on your own computer. 1:29 And it's like, that works. 1:34 I'm getting somewhere. 1:35 Because I think it's useful to have a working model in 1:37 your mind of what the system's doing. 1:41 >> Okay. 1:44 >> And then you can maybe translate that to the documentation a bit better 1:45 later on. 1:48 But just start tweaking example code first. 1:49 >> Okay, so kind of just grab, and most projects have that. 1:52 >> Yeah yeah, yeah, yeah. 1:56 I think it's almost needed if you're going to interact with developers in any way, 1:58 is to have some example projects, and 2:03 sometimes there're these things called kitchen sink projects. 2:06 So I've worked in a lot of different mobile environments where they say, hey, 2:09 here's a kitchen sink application where it shows you all the different menus, 2:13 the different styles of animations, things like that. 2:16 So you can see the thing in action, and then you can maybe find that in the code, 2:19 and then import that into your project. 2:24 >> And then kinda take it and make it your own. 2:26 >> Yeah. >> Okay. 2:28 >> Exactly. >> Neat, so 2:28 you pointed earlier this is IBM Watson,this is what you're 2:29 working on here? 2:32 >> Yes, so Watson is a set of cognitive services from IBM. 2:32 It basically allows you to take input from say human speech or text. 2:37 >> Okay. 2:43 >> And then get the intent and then assign programming functionality to that intent. 2:44 So say for example, in this example I've got the treehouse assistant. 2:52 And it says what would you like to know about, so I could say. 2:56 What is the definition of HTML? 3:00 And Watson responds with the definition of HTML. 3:08 Now I didn't program necessarily the specific wording of what is the definition 3:12 of HTML, but Watson can extract the intent to get a definition. 3:16 And then the coding that I provide can 3:23 decorate the conversation with these meanings. 3:28 >> So it's breaking down the English of that sentence, 3:29 and finding out what it was you actually meant. 3:32 >> Yes. 3:34 >> You could ask that something else- >> Exactly, so- 3:35 >> In a different way. 3:36 >> So you can see here that the intent that Watson found was getDefinition. 3:37 >> Okay. >> And with 94% confidence. 3:44 >> Okay, and getDefinition is something you wrote? 3:48 That's code that you wrote okay? 3:50 >> Exactly. 3:51 >> Can I see that code? 3:52 >> Sure, so. 3:54 The way that Watson works is that you can give it definitions yourself or 3:56 you can let your code give the definitions. 4:02 Or you can give it an HTML document or 4:05 a PDF or a JSON file with other content in, and 4:09 that's called a discovery service. 4:13 So what I first did was getDefinition. 4:17 I wrote all this code myself called handleIntent. 4:25 So I don't know if you're familiar with middleware in web frameworks. 4:28 >> Okay. >> I basically wrote my middleware for 4:33 the conversation. 4:35 So if it can find the definition with me, then that's what you'll respond here. 4:36 If it can't find the definition with the definitions that I have, 4:42 it'll go after the discovery service and discover the meaning. 4:47 So let's look at what my code looks like first. 4:50 I've created this definition resolver and all this does is it 4:53 looks in this definitions file, and then it just extracts itself. 4:58 Let me show you what the JSON looks like. 5:03 It just looks like this. 5:06 So it basically finds HTML, find CSS or JavaScript and 5:07 then gets the definition and spits that out into the check. 5:10 >> Okay. 5:14 >> So that's basically what that definition resolver did. 5:15 And that's a lot occurred. 5:19 >> So this was based on an example project? 5:21 >> Yeah. 5:25 >> Okay, so how did you do that with Watson? 5:25 What's the example project that you looked at? 5:28 >> So the example project was Watson 5:29 simple chats, conversation. 5:34 So here it is. 5:39 >> Okay, cool. 5:42 It's a GitHub. >> It's a GitHub thing, and 5:44 you pull it down and you can check the demo here. 5:46 So this example was to augment a car. 5:49 So turn on the windscreen wipers or something like that. 5:53 Turn on wipers, let's see if this will do it. 5:57 I'll turn on the wipers for you. 6:00 So, this is the initial project that I fought. 6:01 I fought this in and 6:05 then I started augmenting this with the treehouse assistant. 6:06 >> Cool. >> So previously I've worked on an Alexis 6:10 scale that did something very similar. 6:13 >> Right, I thought I was getting deja vu there. 6:15 Okay so the Alexa Skill does something similar to that. 6:17 >> Very similar, it translates the English into an intent, 6:19 which is getDefinition, and then we can grab the definition out. 6:23 >> And these are actually kind of similar, aren't they? 6:27 I think they actually are both called intents. 6:28 >> Yes, exactly, so once you've worked with Alexa, it's easy to 6:31 translate some of those skills over into Watson and these other services as well. 6:36 All of these cognitive services, because if you think about when you speak, 6:42 when you say a sentence, there's always an intent behind it. 6:47 Or when you ask a question there's an intent derived, so 6:51 these cognitive services help derive intent. 6:55 So it can, 6:59 Also get the sentiment behind things and- >> Like 7:01 if you're angry or- >> Yeah. 7:07 >> Wow. >> Yes, say for 7:08 example- >> That's really neat. 7:09 >> You could, [LAUGH], pass all the information through from a chat from 7:11 a custom service representative and a customer, and see their relationship, 7:15 and see if anything can be improved- >> Right, wow. 7:23 >> There and things like that. 7:26 >> This conversation may be recorded and sent through Watson. 7:28 [LAUGH] >> Exactly, 7:32 so this is the project that I branched up off. 7:34 >> And so, let me show you what it looks like. 7:37 So if you look here there's an app.js file. 7:43 And in here there is just this conversation message with a payload. 7:46 And it updates the message and it just sends the response back to the client. 7:54 So that's all that does. 8:00 It just sends a response back to the client, which just happens to be JSON. 8:01 So what I thought was instead of 8:06 making my code all spaghettified inside this message, is to pass the payload 8:12 forward, or the response port forward, and then augment that with my data. 8:18 >> Okay. 8:23 >> So that, that was the HTML, JavaScript, and CSS. 8:23 >> And did you get there because you started following this, and 8:26 were like, this is gonna be. 8:29 This is not good. 8:31 This doesn't feel good to [CROSSTALK] >> Yeah, yes. 8:33 Some of the example code is very like, hey, where should my code live? 8:36 There's no best practices for this stuff. 8:42 It's just, here's an example for you. 8:44 And it works. 8:47 >> Right, it's kinda to spark idea, right? 8:49 >> Yeah. 8:50 >> So now, you've worked on two voice-based apps. 8:51 Do you have any ideas that came from that? 8:54 >> Yeah, definitely. 8:58 Yeah, I want to augment the house with Watson, so that. 8:59 And whether if it's through voice, through Alexa, you can tie that into Watson or 9:02 whether if it's a chat bot that I can just send text messages to or things like that. 9:08 I can basically switch off my the lights around my house because all 9:14 the intents are switch off my lights or turn them on. 9:18 >> Right. >> You can derive the intent from that 9:22 speech. 9:24 >> Like a butler of sorts. 9:25 >> Yeah, exactly. 9:26 >> Okay, cool. 9:27 >> Yeah. 9:28 >> So that butler idea, that came about because you played with this. 9:29 You didn't know how these things worked before, and what you could do with it. 9:34 >> No, and I think that's the whole point is that, 9:38 as soon as you get a model in your mind then you can apply that 9:41 to the world around you, or problems that you're having, or you can see. 9:46 I'm very into JavaScript and the Internet of things, so 9:52 that was a very natural place for me to go with this. 9:55 But I can see that many people who start playing around with this sort of stuff 9:59 if they're working QA, or if they're working support, 10:03 or all these different areas, they can say, well I can augment the experience, 10:06 whether if it's a full pledged AI that can help. 10:11 Like hey, can you tell me my latest order? 10:14 And what's your order number? 10:18 And then it can grab the order number and set from an API and 10:19 send that back in a chat. 10:22 Rather than clicking through the menus of a webpage, 10:24 you can more have a conversation about the thing. 10:27 >> So you kind of follow this methodology all the time. 10:31 You always just dive into the tech, and I am always amazed, what are you doing now? 10:33 You must have started this a long time ago, this practice of just diving in. 10:37 If you could tell yourself, give yourself advice right when you were first 10:43 learning how to code, what would that be? 10:47 >> Persevere, the pain that you go through, it always pays off, 10:50 because eventually something will click in your mind, that that's how it works. 10:54 And literally, you can do anything as long as you persist with it, 11:01 and stay at it. 11:07 But when I say stay at it I'm not saying you should have a break because 11:10 generally a lot of the ha moments is when you go walk away from the computer and 11:13 you go, it's that. 11:17 >> Yeah. 11:18 >> But yeah, definitely that feeling of being uncomfortable that this is hard, 11:19 this is difficult, you'll never understand this. 11:24 Those type of feelings are normal and it does pay off eventually. 11:27 >> All right. 11:31 Thanks, excellent advice. 11:33 >> Awesome. 11:34 >> Thanks for being on the show again, Chalkers. 11:35 >> No worries. 11:36 Thank you. [SOUND] 11:37 >> Check the notes attached to this video 11:42 for links to some great example starter projects. 11:43 Blank slate be gone. 11:46 Thanks for watching the Treehouse Show. 11:47 To get in touch with the show, reach out to me on Twitter, or 11:49 hit us up in the Treehouse community. 11:51 See you next time. 11:52