>> Live from San Francisco, it's The Cube, Covering, Google Cloud Next 2018, brought to you by, Google Cloud and it's ecosystem partners. >> Everyone, welcome back, this is The Cube, live in San Francisco for Google Cloud, big event here, called Google Next 2018, #GoogleNext18, I'm John Furrier, Dave Vellante, bringing down all the top stories, all the top technology news, all the stuff that they're announcing on stage, some of the executives, the product managers, customers, analysts, you name it we want to get that signal and extract it and share that with you. Our next guest is Dan here and he's the product manager for Cloud AI at Google, and dialogue flow with a hot product here under his preview. Thanks for joining us! Good to see you! >> Ah, yeah, excited to be here! >> We were bantering off camera because we love video, we love speech to text, we love all kinds of automation that can add value to someone's products rather than having to do a lot of grunt work, or not having any capabilities, so super excited about what your working on, the variety of things, this one's the biggest, dialogue flow, talk about the product. >> Sure, yeah, yeah. >> What is it? Yeah, so Dialogue Flow it's a platform for building conversational applications, conversation interfaces, so could be chatbox, it could be voicebox, and it started from the acquisition of APIAI, that we did a year and a half ago, and its been gaining a lot of momentum since then so last year at Google Cloud Next, we announced that we just crossed 150,000 developers in the Dialog Flow community, yesterday we just announced that we now crossed 600,000 and yeah its uh-- >> Hold on, back up, slow down. I think I just missed that. You had what and then turned in to what? Say it again. >> So it was a 150,000 last year or over a 150,000 and now its now its over 600,000. >> Congratulations, that's massive. >> So yeah, I-- >> That's traction! >> It's very, very exciting. >> Four X. (laughs) >> And yeah, we you know, were still seeing like a lot of strong growth and you know with the new announcements we made yesterday, we think it's going to take a much larger role, especially in larger enterprises and especially in sort of powering enterprise contact centers. >> You know, natural language processing, also know as NLP for the folks that you know, know the jargon, or don't know the jargon, its been around for a long time, there's been a series of open sores, academias done it, just, it just, ontologys been around, its like, it just never cracked the code. Nothing has actually blown me away over the years, until cloud came. So with cloud, you're seeing a rebirth of NLP because now you have scale, you've got compute power, more access to data, this is a real big deal, can you just talk about the importance of why Cloud and NLP and other things that were, I won't say stunted or hit a glass ceiling and the capability, why is cloud so important because you're seeing a surge in new services. >> Yeah, sure, so there's two big things, one is cloud, the other is machine learning and the AI, and they kind of advanced speech recognition, natural language understanding, speech symphysis, all of the big technologies that we're working on, so with Cloud, there's now sort of a lot more processing that's done centrally and there's more availability of data, that he could use to trains models and that feeds well into machine learning and so you know with machine learning we can do stuff that was much harder to do before machine learning existed. And with some of these new tools, like what makes Dialog Flow special is you could use it to build stuff very, very easily, so I showed last year at Google Cloud Next how you build a bot for an imaginary Google Hardware store, we built the whole thing in 15 minutes, and deployed it on a messaging platform and it was done and its so quick and easy anyone can do it now. >> So Dave we could an ask the cube bot, take our transcripts and just have canned answers maybe down the road you automate it away. >> Yeah, yeah, yeah! >> You'd kill our job! (laughs) >> No its pretty awesome. What's interesting is its shifting the focus from kind of developers and IT more to the business users, so what we're seeing is a lot of our customers, one of the people that went on stage yesterday in the Dialog Flow section, they were saying that now 90% of the work is actually done by the business users that are programming the tool. >> Really? Because a low code type of environment? >> Yeah, you can build simple things without coding, now you know, if you were a large enterprise you're probably going to need to have a fulfillment layer, that has code, but it's somewhat abstracted from the analoopies, and so you can do a lot of things directly on the UY without any code. >> So I get started as a business user, develop some function, get used to it and then learn over time and add more value and then bring in my real hardcore devs when I really want some new functions. >> Right. So what it handles is understanding what the user wants. So if you're building a cube bot, and what Dialog Flow will do is help you understand what the user is saying to the cube bot and then what you need to bring in a developer for is to then fulfill it so if you want that, for example, every time they ask for cube merchandise, you want to send them a shirt or a toy or something, you want your developer to connect it to your warehouse or wherever. >> Give us the best bot chain content you have? >> Right. >> There it is. >> So how would we go about that? We have all this corpus of data that we ingest and and we would just, what would we do with that? Take us through an example. >> So you would want to identify what are the really important use cases, that you want to fulfill, you don't want to do everything, you're going to spread yourself thin and it won't be high quality, you want to pick what are the 20% of things that drive 80% of of the traffic, and then fulfill those, and then for the rest, you probably want to just transition to a human and have it handled by a human. >> So, lets say for us we want it to be topical, right, so would we somehow go through and auto categorize the data and pick the top topics and say okay now we want to chat bot to be able to ask questions about the most relevant content in these five areas, ten areas, or whatever, would that be a reasonable use case that you could actually tackle? >> Yeah, definitely. You know there's a lot of tools, some Google offer, some that other offer that can do that kind of of categorization but you would want to kind of figure out what the important use cases that you want to fulfill and then sort of build paths around them. >> Okay and then you've got ML behind this and this is a function I can, this fits into your servalist strategy, your announced GA today, >> We announced GA a few months ago, but what we announced yesterday was five new features that help transform Dialog Flow into sort or from a tool-- >> What are those features take a minute to explain. >> Sure, yeah, yeah, so first is our Dialog Flow phone gateway, what is does is it can turn any bot into a an IVR that can respond within, it take 30 seconds to set up. You basically just choose a phone number and it attaches a phone number and it cost zero dollars per month, zero, nothing, you juts pay for usage if it actually goes above a certain limit, and then it does all of the speech recognition, speech symphysis, natural language understanding orchestration, it does it all for you. So setting up and IVR, a few years ago used to be something that you needed millions of dollars to set up. >> A science project! Yeah absolutely! >> Now you can do it in a few minutes. >> Wow! >> Second is our knowledge connectors. What it does it lets you incorporate enterprise knowledge into your chat bot, it could either be FAQs or articles, and so now if you have some sort of FAQ, again in like less than a minute, you can build it into Dialog Flow without having to intense for it. Then there are a few other smaller ones that we introduced also are speech symphysis, automatic spell correction, which is really important for a chat box because people always have typos, I'm guilty just as much as everyone. Last but not least sentiment analysis, so when it helps you understand when you want to transition to a human, for example, if you have someone sort of that's not super happy-- >> Agent! >> Yeah exactly! >> And some of these capabilities were available separately so for example you could have built a phone gateway and connected it to Dialog Flow before, but it used to be a big project that took a lot of work so, we had a guest speaker yesterday, in the session for Dialog Flow and they've been running POC with a few vendors right now, its been going on for a few months, and they told us that with Dialog Flow, phone gateway and knowledge connectors, they were able to build something in a few hours that took a few months to do with other vendors because they have to stitch together multiple services, configure them, set them up, do all of that. >> So the use case for this, just to kind of, first of all to, chat box have been hot for a while, super great, but now you have an integrated complex system behind it powering an elegant front end, I could see this as a great bolt on to products, whether it's websites or apps, how-tos, instrumentation, education, lot of different apps, that seems to be the use case. How does someone learn more about how they get involved? Do they go to the website, download some code? Just take us through. I want to jump in tomorrow or now, what do I do? >> There's a free edition I can have right? >> Exactly, yeah, so the good news is you could go to either cloud@google.com/dialogflow or dialogflow.com, there's, if you go to dialogflow.com you can sign up for the standard edition which is 100% free, its for text interactions, its unlimited up to small amount of traffic, and you can even play around with the phone gateway and knowledge connectors with a limited amount, without even giving a credit card. If you want cloud terms of service and enterprise grade reliability, we also offer Dialog Flow enterprise edition, which is available on cloud or google.com, and you can sign up there. >> That comes with an SLA that-- >> Exactly, an SLA and like cloud data terms of service, and everything that's kind of attached with that. I'd also encourage people to check out the YouTube clip for the session that was yesterday that was where we demoed all of these new features. >> What was the name of the session? >> Automating you contact center with a virtual agents. >> Okay check that out on YouTube, good session. Okay so take us through the road map, your on the products, so you're product manager so this is, you got to decide priorities, maybe cut some things, make things work better, what's on the roadmap, what's the guiding principles, what's the north star for this product? >> Yeah, so, for us it's all about the quality of the end user experience, so the reality is there's many thousands of bots out there in the world, and most of them are not great. >> I'll say, most of them really suck. (laughs) >> If you Google for why chat bots, why chat bots fail is the first result, and so that's kind of our north star, we want to solve that, we want to help different developers, whether they're start ups, experience they're enterprises, we want to help them build a high quality bots, and so a lot of the features we announced yesterday, are kind of part of that journey, for example, send integrated sentiment experience that as you transition to humans, cause we know we can't solve everything so helps you understand, or knowledge connectors-- >> Automation helps to a certain point but humans are really important, that crossover point. Trying to understand that's important. >> Exactly, and we'd rather help people build bots that are focused on specific use cases, but do them really, really well, versus do a lot, but leave users with a feeling that they were talking to a bot that doesn't understand them and have a bad experience. >> We could take all the questions we've done on the cube, Dave, and turn them into a chat bot. What's the future of bots? >> Yeah. >> Go ahead, answer the question. (laughs) >> So I think, so we're kind of in the last year or two, we've been at an inflection point, where speech recognition has advanced dramatically, and it's now good enough it can understand really complex questions, so you can see with, sort of Google Assistant and Google Home and bunch of other things that people can now converse with bots and get sort of reasonably good answers back. >> And that just feed ML in a big way. >> Right, exactly, so now, you know, Dialog Flow introduced speech recognition in recognition, which just introduced speech recognition yesterday, and so we're now looking to empower all of our developers to build these amazing voice voice based experiences with Dialog-- >> Give an anecdote or an experience that the customers had where you guys are like wow, that blow me away! That is so cool, or that is just so technically amazing, or that was unique and we've never seen that coming, give us, share some color commentary around some of the implementations of the bot, bot world and the Dialog Flow's impact to someones business or life. >> Sure, so I think yesterday the ticketmaster team was showing how they look at their current idea of that's based in the old world, where you have to give very short response like yes or no or like San Francisco California, and because it's built on these short responses, it kind of a guided IVR, it takes 11 steps-- >> What's an IVR again? >> Integrated Voice Response or Interactive Voice Response, it's a system that answers the phone. >> Just want to get the jargon right. >> So now that with something like Dialog Flow they can go and build something like that instead of 11 steps, takes 3 steps. So because someone can just say, I'd like to buy tickets for so and so and complete the sentence. And the cool thing is sort of the example that they gave a recording that I made with them about a year, plus ago, and the example was, I'd like to book tickets for Chainsmokers and then they were showing it yesterday in the conference, they were like oh we know why you chose it, its because the Chainsmokers are preforming at Google Cloud Next! Its probably just a funny coincidence but... >> So they've deployed this now or they're in the processes of deploying it? >> They're in the process of deploying it, first for customer service, and at a later stage its going to be for sales as well. >> Yeah, because of the IVR for Ticketmaster today, I know it well, I'm a customer, I love Ticketmaster, but you're right, it tells you what you just asked them pretty well, but it really doesn't quite solve your problem well so. >> I mean the recognize the sales one was built a long time ago, but they're kind of overhauling all of that. >> I'm excited to see it because its a good point of comparison, you know good reference point that you understand, it's , the takeaway that I'm getting, Dan, is the advice you're giving is, nail the use case, narrow it down, and then start there, don't try to do too wide of a scope. >> Exactly, exactly. Handle the most important thing is delivering great end user experiences because you want people to really enjoy talking to the bot, so in surveys people say, 60% of consumers say that the thing they want to improve most in customer service is getting more self serve tools. They're not looking to talk to humans, but they're forced to because the self services, yeah they're terrible. >> If can get it quickly self served, I'd love that every time, I'd serve myself gas and a variety of other things, airport kiosks have gotten so much better, I don't mind those anymore. Okay one quick follow up on Dave's point about making a focus, I totally agree, that's a great point. Is there a recommendation on how the data should be structured on the ingest side? What's the training data, si there a certain best practice you recommend on having certain kinds of data, is it Q and A, is it just text, speaks this way, is it just a blob of data that gets parsed by the engine? Take us through on the data piece. >> So that really changes a lot, depending on the specific use case, the specific companies, the specific customers, so someone asked in the adience yesterday, asked the guest speaker has many intense they felt in Dialog Flow and each one of them had very different answer, so it depends a lot. But I would say the goal is to kind of focus on the top use cases that really matter, built high quality conversations, and then built a lot of intents and text examples in those, and when I say a lot, it doesn't, we don't need a lot because Dialog Flow is built on machine learning, sometimes a few dozen is enough, or maybe a couple hundred if you need to, but like we see people trying tens of thousands, we don't need that much data. And then for the other stuff that's not in your core use cases, that's where you can use things like knowledge connectors, or other ways to respond to people rather than to manually build them in, or just divert them to human associates that can fill those. >> Great job Dan! So you're the lead product manager? >> I'm the lead product manager on Dialog Flow Enterprise Edition, and there's a large team kind of working with me. >> How big is the team? Roughly. >> We don't talk about that actually. >> What other products do you own? >> I'm also product manager for cloud speech to text and cloud text to speech. >> Well awesome. Glad to have you on, thanks for sharing. Super exciting, love the focus. I think its a great strategy of having something that's not a one trick pony bot kind model, having something that is more comprehensive, see that's why bots fail. But I think there's a real need for great self service, its the Google way, search yourself, get out quick. Get your results, I mean its the Google ethos. (laughs) Get in, get your answer. >> Yeah, we're all about democratizing AI so now with cloud speech to text and cloud text to speech, put the power of Google speech recognition, speech synthesis into the hands of any developer, now with Dialog Flow we are taking that a step further, anyone can build their voice bots with ease, what used to cost like millions of dollars, you don't need special expertise. >> Alright, Dan Harron is the product manager for the Dialog Flow Enterprise Edition and doing Cloud AI for Google to bring you all the best dialog here in the cube, doing our part, soon we'll have a cube bot, you can ask us any question, we'll have a canned answer from one of the cube interviews. Dave Vellante is here with me, I'm John Furrier, thanks for watching! Stay with us we'll be right back! (music)