How do you imagine a typical voice assistant user?

A 20-something-year-old millennial spending the whole day with his phone or laptop? 👨🏻‍💻

That’s not true.

According to the research, the average user of personal assistant apps is a 52-year-old woman.

Interesting, right?

More of that, voice-activated apps become integral to assisted living communities.

For example, a community of San Diego retirees is using the personal-assistant gadget to listen to audiobooks, keep current with family news, and control home appliances.

The majority of the people in this Alexa focus group are in their late 80s, some use walkers to get around, and some have visual and/or hearing impairments.

They can make calls via voice commands using Amazon’s Alexa-to-Alexa calling service, send and receive text messages and much more.

In a few weeks, this organization will connect the residents’ Echoes to smart plugs and thermostats so they can adjust their lights and room temperature via Alexa.

If all goes well after that two-month test, the company will explore possible deployments of Alexa devices to its other communities.

https://venturebeat.com/2017/08/05/why-the-typical-voicebot-user-is-a-52-year-old-woman/

More info about retirees using Alexa: https://www.technologyreview.com/s/608047/the-octogenarians-who-love-amazons-alexa/

Have you ever bought sex online?

A new bot built by Microsoft employees in their spare time is designed to discourage you from doing that.

The chatbot lurks behind fake online ads for sex posted by nonprofits working to combat human trafficking and responds to text messages sent to the number listed.

It initially pretends to be the person in the ad and can converse about its purported age, body, fetish services, and pricing.

If a would-be buyer signals an intent to purchase sex, the bot pivots sharply into a stern message.

Quite an interesting use case for a chatbot, right?

To be honest, every day while researching the internet for a new content for the channel I come across plenty of different ways to use chatbots.

What’s the most interesting you’ve seen so far?

Let’s discuss in our chat - @botcubechat.

https://www.wired.com/story/microsoft-chatbot-trolls-shoppers-for-online-sex/

Hey folks, I think I need your help right now.

I curate one of the biggest resources containing everything about bots - https://github.com/BotCube/awesome-bots.

But the main part of it was created about 3-4 months ago and I see that many of you have created a plenty of useful services, tools, frameworks, articles helping to build great bots during this time.

So I need your help to add the content I've missed.

Please share any piece of value related to bots you've created and I'll add them to the list.

It can be anything from guide to bot building platform.

You can contact me here - @maximabramchuk.

Let's go!

What is the best platform to build a Facebook Messenger chatbot without coding?

That’s quite hard to say.

But there are definitely 2 leaders in this field - ManyChat and ChatFuel.

But what’s the difference? Pros and cons? Unique features?

Article below evaluates both platforms with a list of 14 criteria.

Super comprehensive, right?

The main purpose of the article is to help you pick the platform that works best for your business.

It covers everything from pricing and plans to AI/NLP support and payments integration.

Guys, it’s a golden gem that will save you days of work.

Enjoy!

https://www.thinktuitive.com/comparison-manychat-vs-chatfuel/

I have a lot of buzzwords for you today, guys.

Most of you probably knows the bot called Sensay - a bot that connects users with other people for anonymous advice.

They decided to monetize their bot by creating their own cryptocurrency based on Ethereum - SENSE.

Today, advice givers can receive tips in the form of tokens, and roughly 20 million coins have been awarded already.

Once SENSE becomes available, “coinholders will be immediately rewarded on a 1:1 basis”.

The currency may be made available to bots, apps, and services beyond Sensay in the future.

SENSE is the second cryptocurrency launched for the bot ecosystem in recent months.

This spring, chat app Kik also announced plans to create its own cryptocurrency, called Kin.

I love this trend when you can transform your virtual coins/tokens inside the app/bot into a real cryptocurrency.

I think it will help a lot of products to solve the monetization issues.

https://venturebeat.com/2017/08/12/sensay-advice-bot-to-launch-ethereum-based-cryptocurrency/

Intercom has launched Operator, which is a #botoftheweek for customer experience.

Why do they need a chatbot?

Intercom makes products that help businesses to communicate with their customers. The bot’s goal here is to automate some extremely simple tasks around this communication, which the bot can handle better/faster than live operators.

For example, if someone is texting business on a website, and that business is now overnight, nobody will pick up the chat. In this case, the bot could clarify the situation and ask for the best channel to follow up when the team will be back in the office.

Just like Amazon Alexa, Operator has a growing set of skills, including:

- Set expectations based on your team’s availability
- Collect contact information
- Intelligently suggest help articles to answer questions
- Automatically close answered conversations for you
- Measure customer satisfaction

It’s just the beginning, the next step is to add some kind of SDK/framework available for teams to build their own skills 🤖

https://www.intercom.com/operator-bot

Landing pages are not working anymore as well as they did.

Abundance usually leads to inefficiency, which is precisely what’s happening in the landing page landscape.

When everyone makes good looking landing pages, the user expectation is changing.

That’s why companies is suffering from an average conversion rate of 2,35%.

But here is the thing that can help - conversational interfaces.

There are different ways conversational interfaces could make a big difference in your landing page conversion:

1. Increasing user engagement - in the case of conversational inteface, we have a simple and in crescendo storytelling flow where information is provided progressively under user’s request.
2. Greater user personalization - with conversational interfaces we could make each user interaction as personal as possible via asking questions and using this data further.
3. Real-time lead qualification - in a conversational interface, the information flow works in both way by providing and asking data from users in order to validate the fit with your company’s current focus.
4. Differentiation from the crowd - using a conversational interface can help to position yourself as an innovative company and stand out from the crowd.

Take a look at the article below explaining all these points, it’s a golden gem 😉

https://chatbotnewsdaily.com/landing-page-as-chatbot-why-lead-generation-is-the-killer-app-for-conversational-interfaces-1d2c60d2ddfa

Why Amazon’s Alexa voice assistant beat Cortana and any others? 🤔

Microsoft’s former AI expert, Qi Lu, has provided some rare insight into Microsoft’s struggles to compete with Amazon’s Alexa voice assistant.

“I worked on Cortana four and a half years ago. At the time we all were like, Amazon, yeah, that technology is so far behind”.

“Google and Microsoft, technologically, were ahead of Amazon by a wide margin. But look at the AI race today. The Amazon Alexa ecosystem is far ahead of anybody else in the United States.”

Lu believes Microsoft and Google “made the same mistake” of focusing on the phone and PC for voice assistants, instead of a dedicated device.

Microsoft first introduced Cortana ahead of Alexa as a promising digital assistant for its Windows Phone devices, then expanded it to be built into Windows 10 for PCs and into the company’s Xbox One console.

Cortana will also run on various Internet of Things (IoT) devices like fridges, toasters, thermostats, and even cars in Microsoft’s latest bid to catch up and beat Amazon’s popular Alexa voice assistant.

https://www.theverge.com/2017/8/14/16142642/microsoft-cortana-amazon-alexa-qi-lu

Amazon is going huge on building community around their voice assistant 📈

Amazon Alexa team has recently launched a program in partnership with Arizona State University (ASU).

The program itself is designed to enhance students’ ASU experience by giving them touch-free access to information and services tailored to campus living — and prepare some of them to become leaders in voice-technology development.

Incoming freshmen engineering students will be able to build their own Alexa skills or capabilities and join the growing community of voice developers.

“Our focus is putting this technology into the hands of our students in a way that will build an ecosystem that supports voice technologies throughout the ASU campus.”

I’m pretty sure that ASU is a perfect fit for Amazon because it has been ranked No. 1 in innovation by U.S. News & World Report for two years in a row, staying the course by embedding innovation into its schools, departments, athletics and student experiences.

I’m really pumped to see how Amazon is building an ecosystem around voice by doing such a program, that is a really smart move from these guys 👍

https://asunow.asu.edu/20170817-asu-news-asu-amazon-dots-tooker-house

Here’s one video from the last F8 conference that everyone missed.

It deeply covers the death of decision trees, webviews, structured menus, and chat extensions.

Incredibly helpful for beginners.

Here's the link: https://developers.facebook.com/videos/f8-2017/how-to-build-a-great-bot

Zendesk has just released their new #botoftheweek for customer support automation.

Boom!

I’ve seen a lot of startups trying to do the same thing, but it was only a matter of time before the big players made it a feature.

What’s interesting here is that both Intercom and Zendesk position their bots less as bots or conversational assistants and more like a knowledge base products.

That makes a lot of sense — there’s so much value in the content assets that customers have already created and sometimes it's just about helping connect the dots.

Top 4 features of Zendesk bot:

1. It works wherever your customers are: Answer Bot already works across several channels including email and API which typically don’t have great automated self service experiences. They’re also extending Answer Bot to create new in-channel experiences for web form, web widget, chat, and our SDKs in the near future.

2. Activate and go: They’ve removed the complexity to make it as easy as possible for anyone to start using Answer Bot straight away. No training time or massive data sets needed. (You’re wondering how? Because it’s trained on over 12 million customer service interactions to deliver accurate and reliable responses. And it’ll continue to learn and grow.)

3. Learns from customers and agents: Interactions between Answer Bot and your customers are clearly presented to your support team, allowing them to see the actions customers have taken to avoid suggesting the same content again. Your support team can also provide pointers to Answer Bot to help it learn over time.

4. Optimize performance with reporting: Generate amazing insights into where Answer Bot performs well and where you may need to create or improve your self-service content.

Let the automation battle begin! 🤖

https://www.zendesk.com/answer-bot

Have you always been thinking about creating a bot for Google Home?

It’s never been easier!

A couple of Google Assistant Developer Program engineers has just launched a template tool to create trivia games for the Google Assistant.

The template turns your questions and answers from a spreadsheet into a fully functioning game without writing any code.

Isn’t that cool?

1. Pick a Persona.
2. Enter your data to a Google Sheet template.
3. Set up your project in Google Actions console.
4. Test your app.
5. Submit your app.
6. Let the game begin.

It is also open-source so you can add your own features too.

Enjoy and have fun building voice bots 😉

https://medium.com/@leonnicholls/google-assistant-trivia-template-d0e5d12fc200

Template: https://triviatemplate.com/
Template source code: https://github.com/actions-on-google/apiai-trivia-game-nodejs

Over the past few months, it’s been all but impossible to escape the growing buzz around voice technology. From Amazon’s Echo to Google Home to Apple’s HomePod, it seems like everyone’s getting into the game.

Here is an article from Alon Bonder, VC at Venrock, that presents an overview of how space has evolved, and a few areas he is excited about for investment.

The most interesting part of the article for me personally is a list of native advantages of the voice in general with areas that worth trying to build project in.

If you’re interested in voice - really worth reading or at least adding to your Pocket to read during the weekend, I promise 😉

https://medium.com/startup-grind/why-voice-tech-is-about-to-see-major-love-from-vcs-341a9b05cc2b

OMG, this is just hilarious.

Excited about the future of voice interfaces ;)

https://www.youtube.com/watch?v=YvT_gqs5ETk

Google is not gonna give up in the voice assistant game 🥊

They are reportedly planning to release a smaller version of its Google Home smart speaker later this year.

The features available in the mini Google Home are not yet known, but if the reports are true, Google Home could be complemented by a series of smaller, potentially cheaper speakers that you can place throughout your home.

This is similar to how Amazon Echo owners can leverage Echo Dots to spread voice control and music throughout their homes.

A survey conducted earlier this year found that price was the single most important determinant in whether consumers buy a smart speaker.

That’s probably why the $50 Echo Dot was the top selling item on Amazon’s Prime Day in July.

A lower-cost Google Home — which at $129 is cheaper than an Echo ($179) but more expensive than two Echo Dots — could help Google compete against Amazon and other tech giants who plan to launch their own smart speakers in months to come.

https://venturebeat.com/2017/08/21/google-is-reportedly-working-on-a-smaller-smart-speaker-to-take-on-amazons-echo-dot/

Facebook Messenger now supports markdown!

You can style your messages on messenger.com and facebook.com, no iOS/Android support yet.

HINT: _text_ is italic, *text* is bold, `text `is monospace.

What do you know about the conversational design?

If you do know a lot - let’s talk (@maximabramchuk) 🙃

If not - I have a golden gem for you today.

The article below contains a case study describing an entire process of designing a conversational UI for a B2B website, including fragments of the conversation noscript, basics of the communication theory and some of the tips and tricks that can make the project a bit unique.

It’s quite long, but trust me - this thing is really interesting and insanely useful.

https://medium.com/swlh/conversational-ui-principles-complete-process-of-designing-a-website-chatbot-d0c2a5fee376

Just found a great video for you guys.

Here Amir Shevat, the head of developer relations @ Slack, is talking about bot anatomy.

He covered some interesting details of the Slack platform, bot users, conversational design, and shared his own tips & tricks for designing bots.

“When you are writing an onboarding for your bot, think about it as an onboarding of a new employee to the team. How do you onboard them? Use the same paradigm, the same way of thinking to onboard a bot.”

Have a great weekend! 🤖

https://youtu.be/8zBSJg62hRI

We need your help! 🙌

We’re working on a product for conversational design and I know there are a lot people here who designed/prototyped bots and conversational interfaces.

If you’re one of those people - please fill in the Typeform I attached below, it won’t take more than 10 minutes, but will be insanely helpful for us.

P.S. Every bot designer who passes the survey will get an early access to our conversational design tool.

If you have any questions or suggestions - feel free to ask me (@maximabramchuk).

Thank you!

https://maximabramchuk.typeform.com/to/OqqEwp

Do you want to know which Speech Recognition API is the fastest one?

Here is a great article that presents benchmarking results for three speech to text providers:
1. Google Cloud Speech API
2. IBM Watson
3. Microsoft Speech Bing API

According to the results, Google Cloud Speech seems to be the better solution as they have the most accurate and consistent results, but it is the most expensive.

IBM Watson suffers a big drop in performance when working with French speech.

Moreover, the response time is way too high for real-time usage.

Microsoft is in the middle with a good response time.

If you want to learn more, here is the article with comprehensive denoscription: https://chatbotsmagazine.com/you-shall-not-speak-benchmarking-famous-speech-recognition-apis-for-chatbots-1c04e8ce2c66

We are moving closer to bots on WhatsApp

WhatsApp is beginning to verify business accounts with a green badge next to the user’s phone number.

“If you see a green badge next to a contact’s name, it means that WhatsApp has confirmed that the phone number of this contact belongs to a business account”.

Conversations with businesses will also be distinguished from others because all business messages will come in yellow.

It doesn’t look like a really big deal, but it appears to be one of the first signs of WhatsApp’s effort to connect businesses with customers.

Since WhatsApp is insanely popular in a big number of countries, that will open up a plenty of opportunities for bot builders.

These guys are reportedly testing the platform since the beginning of the year, so let’s hope they’ll finally release something soon 🙌

https://venturebeat.com/2017/08/29/whatsapp-is-verifying-business-accounts/