The Alexa Podcast - Episode 1
Co-hosts: Bradley Metrock (CEO, Score Publishing) and Kevin Old (software developer, LifeWay)
Guest: Octavio Menocal, RAIN Agency
Duration: 27 minutes, 29 seconds
Bradley Metrock: Hi, and welcome to the first-ever Alexa Podcast.
My name is Bradley Metrock. I'm CEO of a company called Score Publishing, based in Nashville, Tennessee. We have the mission of helping people become better interactive content creators, and we've gotten involved with Alexa. We run the annual Alexa Conference.
My co-host is Kevin Old.
Kevin Old: Hello.
Metrock: And tonight, we have on as our first guest ever, Octavio Menocal of RAIN Agency in Nicaragua.
Octavio Menocal: Hello Bradley, thank you.
Metrock: Octavio, we're thrilled to have you, and really thrilled to be launching The Alexa Podcast, period. The Alexa Podcast is one of a few shows that we're starting with on the new VoiceFirst.FM, our podcast network. We're going to bring a variety of content, as far as podcasts go, related to voice-first technology. Alexa, Google, AI, bots, all sorts of stuff, and how all that intersects with different industries.
We'll have a show called The Voice of Healthcare, we'll have a show called The VoiceFirst Roundtable, and we've got some other exciting shows coming your way.
But let's get to The Alexa Podcast. This is going to be a half-hour-ish, every month or so, related to Alexa and how Alexa is impacting different industries or different sectors and we're going to have a guest on each show to talk about what he or she is doing with Alexa.
And so Octavio, let's start with how you got into developing for Alexa.
Menocal: Sure thing, Bradley. It was super-exciting getting into this Alexa world. It was by the end of 2015 I started at RAIN as an Android developer, but then, we were introduced to the Alexa development. We got a series of webinars on how the platform worked by then, and we received technical instructions and we received user experience workshops too, because it was a completely different world. We didn't have a screen. It was just voice.
And it was super, super exciting for me that I have over a year working with Alexa skills, not only at RAIN, but personally as a developer.
Metrock: Yeah, you developed a number of big-time skills - and sorry to interrupt you there - but Campbell's Soup, 1-800-Flowers, Safeco...what was your favorite one to develop?
Menocal: (laughs) I have loved every one of them, because it's been a completely different experience. From developing my first account project, to long-form audio skills like GE Podcast Theater, but personally I love our work on the Tide skill, because we integrated messaging with Twillio, and the Tide skill sends images in the messages to the users with instructions on how to get rid of any kind of a stain. So I can tell you, that is my favorite one.
Metrock: And you're talking about Tide detergent?
Menocal: Yes, exactly. The stain remover.
Metrock: Cool. So RAIN Agency, the company you work for down in Nicaragua, is one of the Amazon "preferred' Alexa developers that Amazon has listed on its website. How did that come to be?
Menocal: We at RAIN are the very first partner with Amazon to develop Alexa skills, and RAIN has three offices: one is in Utah, the other one is in New York City, and we have one down here in Nicaragua / Central America. And so everything started with Campbell's Kitchen, that has been an old client. We have developed several works for them, like their website and their mobile application. And then, thanks to their research department, based in New York, they decided to implement another technology, and they saw in Alexa a huge opportunity with Campbell's.
And Campbell's Kitchen is the very first recipe skill, and so far it's been really, really good - a nice experience, not only for the user, but also for us. We learned a lot from them.
Metrock: So a company comes to you, or comes to RAIN Agency - you know, a Safeco, or a Tide, or whoever - and they tell you what? They tell you that they just want to do an Alexa skill? Or that they want to have some sort of voice skill, without even mentioning Alexa - you know, cross-platform? How does that conversation begin?
Menocal: At the beginning, it is just companies that would like an advertisement solution with RAIN. And then, RAIN makes research, and we always try to incorporate new technologies to offer to the client. And if we see the opportunity to build an Alexa skill, that's what we do. And sometimes it's the client reaching to us, and other times it's Amazon who recommends to the client "hey, we have RAIN Agency as a partner, and you can go with them to develop a skill."
Kevin Old: So Octavio, can you walk us through how you go about designing the voice interface that a user would interact with, via Alexa?
Menocal: Yeah, sure, definitely. So I'm going to tell you my developer point-of-view, since when there is an Alexa project, there are a lot of people involved. We even have a voice experience department. By voice experience, I just mean the same user experience oriented to the voice.
These guys are awesome - they just think through the idea of the need of the client, the type of clients for the companies, and they start building the instruction model. Well we know developers of the instruction model, the voice experience guys at RAIN develop that part, and then they explain to us, to developers, the intent, the utterances they want to map, the slot types involved in the experience, and based on that, we start the development.
And some more information is that they build the entire flow of the skill. We have some diagram tools to develop the skill to follow the instructions. Every response is reviewed by the voice experience department, and after everything is approved - we even talk to the client sometimes to discuss about some responses - once all the parts are agreed, that's my turn to start developing the skill. Once we're done, we send the skill to the client for the first approval, and then we send it to the certification - to Amazon.
Old: Awesome. I know that's a different area for me, and I like how your company has formed a voice experience department, as you mentioned, in the same spirit as a UX designer.
Menocal: Yes, yes.
Old: Can you talk about any challenges that you've run into, with developing a voice experience? Are there any of those "gotchas" that you've run into that you think would help others, or that you found interesting?
Menocal: Yeah, sure. Well, I'm going to tell you that the blocker at the beginning was that, at the beginning, there was not too much examples of projects out. So we had to build everything from scratch, for the first project. And it was also difficult to test our skill in the Alexa developer portal, until we started using a tunnel tool which redirects the Alexa skill to our lotto machines. So at the beginning, it was a waste of time trying to call a Lambda function and then come back and start testing. It was a complete waste of time, but thanks to a tunnel tool - it's really cool - then we saw there were not many tools out for use, and we decided to implement our own framework, so if you haven't heard about that, it's called Voxa.
We have been working on it lately and it's out and it's free for any developer to use, and we released examples and we hope everyone will try it out to see if it's a good fit for them. We love working for Voxa - it's the framework we use. And yeah, probably at the beginning, the most challenging part was the lack of examples, but now, that is in the past.
Old: That's awesome. We'll certainly put that in the show notes, and I'll certainly dive into it.
I heard you mentioned Lambda. So do you host all of your skills on Lambdas, or do you have proprietary APIs that you interact with?
Menocal: Yeah, all the code we relay on the AWS ecosystem, so we always try to use the tools available on AWS. The main one is Lambda. You know, one of the main things of Lambda is that it's super cheap, it's super scalable, and it connects to everything in AWS. So yeah, that's what we use in every project. It's what we recommend to the client, and it's super easy to set up. That's the tool that we use, always with the Voxa framework.
Another thing that I would like to tell you guys...yeah, go ahead Bradley...
Metrock: No, keep going.
Menocal: Oh, ok. I wanted to talk to you about Reverb - that is our mobile application where we integrated Alexa into the phone. So far, it has over one hundred thousand downloads in every store - Google Play, the App Store. At the beginning, we built Reverb for our own testing, because as I mentioned at the beginning, it is not just developers. There are a lot of people involved - there are voice experience guys, there are the project managers of the project, so we all want to test the skills anytime, anywhere, where we are. So we started building the Reverb mobile application, and now it is a huge success, because any Alexa user loves talking to Alexa through Reverb. We use it every time, not only with the Echo devices, and it's been just awesome.
Metrock: Cool. So thank you for sharing that with us. I want to shift gears for a moment to this week's news, which it seems like there's been almost too much to keep up, in terms of what's going on with Amazon and Alexa and voice-first technology.
The first thing I want to start with is the Echo Show, which is the hardware that Amazon announced that pairs a screen with the Echo. And then the other announcement, that at least caught my eye, was the Echo Look, which is the camera which did generate some controversy, that's intended to go in your bedroom. The way I understand it at least, will help people with their fashion sense...
Menocal: Yeah, it will recommend you what to wear (laughs)...
Metrock: Yeah, and my wife, I knew she'd be interested in it, and sure enough, I didn't know that Amazon was advertising the Echo Look on the front of their website, but they were. And she asked me "what's the Echo Look?" And she was looking at it, and I was interested to hear what she had to say. She didn't mention any privacy concerns, she didn't mention anything - she just wondered if it worked. I thought that was interesting.
Octavio, my question for you is between the Echo Show, and the Echo Look, I'd love to get your reaction to both of them, and which one of the two you think will have a bigger impact in 2017.
Menocal: Definitely, it's been great announcements by Amazon. We all are real excited about these new devices, because I think somehow it changes the rules of the game we've been playing. With connected devices, there's no screen, it's just our voice trying to talk to another human inside the Echo. But now, we have cameras inside, with the Echo Look. We have a screen with the Echo Show, which now it will help us a lot to offer our users a way better experience with a skill. But I personally think the Echo Show will hit the nail this year. I think from what we have seen in the videos, and if you have maybe bought it, it can play videos, it can show images instantly, so it will be like a teacher, not only talking to us, but showing us interactive images or videos. People will love that.
Maybe the Echo Look will be just a middle tool for anyone trying to look better, to get a suggestion...
Metrock: Now see, the thing about that is Amazon has played up the fashion angle to that device. But the reality is, I don't think fashion is even in the top three, four, or five things that that device ought to be used for. I mean, to me, the number one thing that a device like that could be used for is health care. And I've seen some people talking about it, sort of negatively, saying "what data is this device capable of capturing about your health?" Obviously, it's capturing what you look like, and the visuals are health data in and of itself. But if that were used the right way, that'd be a very powerful...you know, it could have a lot of health care potential. Not to mention how it might fit into any number of other industries, where a camera filming you, in conjunction with the voice interaction...I don't know, it just opens up an entire new world that in no way, to me, is captured at all by just saying "this is a fashion device." Maybe that's just Amazon playing coy. I mean, I'm sure they realize the potential of it. But they've got to get into people's bedroom first, and I guess maybe they've figured out that's the angle to play, I don't know. What do you think?
Metrock: Well, and even things like...one of my favorite apps of all time is Shazam. Do you know what that is?
Menocal: Yeah, I've heard about it.
Metrock: So Shazam is a mobile app that listens to music that's playing, or audio...primarily songs, you know, commercially-released music...and it tells you what it is. It tells you the song name. It tells you the artist. It identifies it for you.
One of the things that intrigues me about the Echo Look, is the opportunity to do ... and even with the Show, I'm sure cameras will be built into all these devices out of necessity ... but the opportunity to create recognition capability in the software.
One thing that comes to mind is you did a skill for Campbell's Soup, right?
Metrock: So if I'm making some Campbell's Soup in my kitchen, it would be cool ... and maybe soup's not the best example ... but if I'm cooking a dish, wouldn't it be cool if the camera can recognize ...
Menocal: The ingredients?
Metrock: Well, recognize the ingredients, and help you with quantity and the composition of it, but also the cooking, and looking in the oven, and, you know, saying "hey, it looks like this is getting burned..." It just opens up a lot of opportunity.
Of course, cynics will say it's privacy violations, and maybe that's true, but, I don't know, that type of thing gets me excited, just the potential for having a camera and what it could do just to help people, in conjunction with the voice interaction.
Menocal: I think, if you're open-minded, you can get the most out of the device. Just as you're right now suggesting, you can come up with any important use in your house, in your work, in your daily activities. So I think I would love to see what people in social media thinks about what they are using the Echo Look for.
Old: Yeah, I'd like to jump in ... I think there are some practical uses for the camera, as we've been talking. In relation to cooking, I can see a number of things. If you want to add soup or something to your grocery list, if you would hold it up to the camera, and say "Alexa, add this to my shopping list," or to-do list or something like that, it would be able to recognize that it's Campbell's Soup, or a certain type of crouton, or spice, or something like that, and add that specific thing to it.
I also think that the Echo Look, at first...the fashion commercials that they came out with, those did not really attract me. I did think that it was a bit weird at first. But then, simply identifying products, either to purchase or if you could hold it up and say, "hey, I'd like to buy two more of these," I'm certain Amazon would automate that purchase through their system.
As far as the Echo Show goes, as soon as I saw it, I had a memory pop in my head from probably the early 90's, or late 80's. There was a thing that I believe it was AT&T was coming out with, called the Video Phone, and it was not well received. Obviously, it was before its day. But the idea was that you would buy a phone, and it would have a screen in the phone. We really didn't even have actual cell phones that worked, much less what we have today. You know, FaceTime, and Skype, all those are commonplace, so I feel like that dream, I guess, to have a phone where the grandmother can talk to the grandkids, I think that's finally come full-circle with this infrastructure.
I agree with Octavio, I think there will be a lot of use out of that, just for use in the commercial, and then I do see it as an aid in the kitchen specifically. If you're cooking something, you can use Alexa to say "hey, Alexa, what's the next ingredient?" and it would be able to use the card technology to be able to slide the next ingredient, or turn the page. And turning the pages, in developer-speak, would be additional cards, or additional images, that would be put on the screen. So I could see that as a big advantage in the kitchen.
Metrock: So we'll go ahead and wrap up. And Kevin, it occurs to me we never said who you are at the start of this.
Kevin Old spoke at the first Alexa Conference, he'll be speaking at the next one, he'll be my co-host on The Alexa Podcast, and he's a software developer for LifeWay, here in Nashville.
Octavio, we're thrilled to have had you on the podcast. Thank you very much for being our first guest ever.
Menocal: I appreciate it, Bradley.
Metrock: Yeah, thank you so much for setting the time aside for us. And Octavio will be a speaker at the next Alexa Conference, which will be in January in Chattanooga. Chattanooga's a very up-and-coming city. It's a perfect place to have this type of conference. It's equidistant from a number of key cities, but we'll have people coming from both coasts, as well as internationally to attend.
It will be Octavio's first time in the United States, correct, Octavio?
Menocal: It will be, it will be, certainly.
Metrock: That's exciting.
Menocal: I'm really looking forward to being there.
Metrock: Yeah, so it's exciting to have somebody with Octavio's expertise join us, as part of our programming lineup. It's just going to be a phenomenal event. You can check out more information on that at AlexaConference.com, or on Twitter at @AlexaConf.
Thank you very much, Octavio. Kevin, appreciate it. Until next time.