Google is rolling out RCS messaging and partnered with BT to bring conversational messaging on Android to life. And it’s good! read more
Frank Schneider, CEO of Speakeasy AI joins us to share how you can automate your call centres using conversational AI.
Mindsay CEO, Guillaume Laporte joins us to share how you can use conversational AI to improve and scale your customer care and support.
Win free tickets to All About Voice 2019
To be in with a chance of winning one of two free tickets to the event in Munich on October 11th, all you need to do is:
Send a tweet using #AAV19 and tell us your favourite voice experience of 2019 so far.
Winners will be announced on next week’s show!
In this episode
We dig deep into how conversational AI is helping some of Europe’s biggest airlines scale their customer care operations, and give you some food for thought as to how you could do the same for your industry or clients.
Guillaume also shares with us some of the best surfaces to implement conversational AI, as well as some of the most successful use cases to focus on and where you should start when thinking of introducing conversational AI for the first time.
We discuss the differences between customer care and customer support and the future of the two in a voice-first world.
We speak to the creator of the world’s best chatbot about how to design Loebner prize-winning conversational experiences.
13 years in the making, Mitsuku convinced a panel of judges that it’s the most humanlike bot over the course of a 20 minute conversation, two years in a row, to be crowned the world’s best chatbot and conversational agent.
It’s featured in the Wall Street Journal, BBC, The Guardian and Wired. And, unlike most chatbots that focus on serving a specific set of use cases, Mitsuku is a general conversational agent. That means you can speak to it about anything.
This week’s Flash Briefing question is from Brielle Nickoloff of Witlingo: What would an open source voice assistant look like? Send us your thoughts and you could feature on the VUX World Flash Briefing this week!
What about voice?
Although Mitsuku is a text-based chatbot, this episode looks at how to take Steve’s 13 years of experience in creating conversational experiences and apply that to the voice first space.
In this episode
This episode is all about how to design and create a world-leading general conversational experience.
We get into detail about how Mitsuku is built (hint: it doesn’t use natural language processing or machine learning like most other conversational AI) and how Natural Language Processing-based conversational agents don’t quite hit the mark.
Steve tells us about Mitsuku’s rule-based supervised learning and how that’s leading to better experiences.
Despite Mitsuku passing the Turing test, Steve tells us why the Turing test is redundant.
We discuss user behaviour and how people treat a general conversational agent, from counselling to romance, bullying to marriage and money worries, and how to be sensitive on those topics.
We hear how varied responses can increase engagement. So much so that one person has spent 9 hours talking to Mitsuku!
We find out how to deal with pronoun resolution and how to refer back to what was said earlier in the conversation.
We uncover how brands are using Mitsuku as part of their conversational experiences, handing off to her when a user strays away from the use cases that their bot can handle.
We chat about how Alexa fairs against Mitsuku as is shown in this video:
And hear where Siri would have finished if it was entered in to the Loebner prize competition.
Perhaps one of the most valuable lessons in this episode is the importance of persisting. Creating a conversational agent, a true conversational experience, takes time. It’s not a quick fix that you cobble together with a quick Alexa Skill. It takes years of development, iteration and constant improvement. But, if you stick with it, you might end up with the next best conversational agent.
Steve Worswick started out in IT support and built Mitsuku as a passion project on the side. 13 years of hard work and 3 Loebner prizes later, he’s now working at the world’s largest chatbot agency and provider, PandoraBots.
Where to listen
- iTunes/Apple podcasts
- Any other podcast player you use or ask Any Pod to play VUX World on Alexa
Check out Mitsuku on Pandorabots
Check out Steve’s talk at the Chatbots and Voice Assistants London event
Conversational AI crops up constantly in conversations about voice, but what actually is it? How the heck does it work? And how can you use it? We speak to Jeff Smith to find out.
In this episode, we cover:
- An overview of conversational AI – what it is and how it works
- The role of conversational AI in voice
- How and why brands should consider using it
- How you can get started with machine learning and conversational AI
- Challenges and opportunities such as the state of analytics and security
At the foot of the show, I said this was:
“One of the most interesting conversations I’ve ever had in my life.”
And I wasn’t lying.
Getting to grips with Conversational AI
If you’re not familiar with the concepts of conversational AI, this episode will give you a great introduction.
If you are familiar and work in the industry, Jeff drops some great nuggets and learnings from his extensive experience.
And if you’re interested in this from a branding perspective, by the end of this episode, you’ll have a full understanding of the contexts and environments where it’s useful.
Jeff Smith, author of Reactive Machine Learning Systems, has bags of experience in the area of machine learning and conversational AI. He’s built a series of AIs, including Amy and Andrew at X.ai (what a cool domain!). That’s an AI Personal Assistant that helps people schedule meetings.
Jeff now works with IPsoft and manages the conversational AI team who’re building Amelia. Amelia, as you’ll find out in the show, is an extremely sophisticated AI that can perform many human tasks, increasing productivity and business efficiencies.
- Jeff’s book, Reactive Machine Learning Systems
- Jeff’s talks and content on Reactive Machine Learning
- Follow Jeff on Twitter
- IPsoft website where you can check out Amelia
- Follow IPsoft on Twitter
- Jeff’s article, ‘Better conversations with machines‘
- Check out Jeff on Medium
- Hear Donald Trump on Lyrebird
Or search “VUX World” in your chosen podcast player!