Close Ad

The Spoon

Daily news and analysis about the food tech revolution

Bot

Behind The Bot: Meet Sure, A Chatbot That Recommends Instagram Food Hotspots

While some people get downright grumpy when it comes to seeing food pics posted in their Facebook and Instagram feeds, I’m one of those that actually enjoys them. In fact, when I see someone showing off a tasty platter from a local restaurant on Instagram, I’ll often make a mental note to check that place out if it’s in my town or somewhere I plan on visiting soon.

If you use Instagram food posts as a restaurant discovery tool like me, I have good news: there’s now a bot that looks for Instagram hotspots and surfaces them in the form of restaurant recommendations. The chatbot is called Sure, and it’s a Facebook Messenger chatbot that curates the most Instagrammed food and drink spots in your neighborhood.

I interviewed the Juraj Pal, the CEO of Sure, to hear about how the idea for the bot came together.

Where did you get the idea for your bot?

Our motivation was simple. We weren’t satisfied with the existing restaurant discovery and travel apps and we quickly started believing that we can build a much better product for the next generation, already spending more time in messaging apps.

Having grown up with internet, we have soon learnt that virtually anything was accessible on our fingertips. It opened up a whole world of opportunities for us. But at the same, it made us feel overwhelmed with choices and options.

At first we actually started with a spreadsheet full of restaurants, cafes and bars that we curated ourselves. And to validate the idea, we launched a simple SMS bot where users would text our number and we would reply manually to each message, recommending a spot from our spreadsheet.

By tying visual social content to specific food locations, are you tapping into how you think this is how Millennials and others choose food?

We knew that others tried to solve this problem and the space is crowded with big players like Yelp or Foursquare. But we truly believe that for the new generation, they just don’t get it.

We quickly learned that millennials trust their friends and influencers more than reviews from strangers on Yelp. Rather than providing endless results like Google, we turned to Instagram as our primary source of all recommendations.

Why did you choose to use Facebook Messenger vs other platforms?

Other than having 1.2B monthly active users, Facebook Messenger is inherently social which makes it easy for people to share with their friends.

The social aspect has however been important also from another angle. When it comes to choosing a place to eat out, majority of the people ask their friends or influencers who they can relate to. By being on a platform where our users naturally chat with their friends, chatbot has the potential to blur the lines between tech algorithms and word of mouth recommendations.

What is unique about developing for a chatbot vs. other AI platforms?

We’ve seen different roles evolve as we were building the chatbot. We for example spend much more time on copywriting and building the bot’s persona and empathy than designing flows.

Building chatbots also costs less and happens much faster. And this in turn allows us to ship our product faster and iterate based on feedback we get. And what I love the most about this experimentation is that we’re focused on value delivery, rather than building potentially useless product features.

Why a food-focused bot?

We decided to start by answering the ‘Where shall we eat?’ question once and for all. Food is a highly personal choice that represents who we are and ties us with a community. Also, in the digitalised world we live in today, eating out is one of the few experiences that we cannot replicate online.

And since people are used to asking their friends for food recommendations on Messenger, we though we could be that concierge friend for everything when you’re out an about.

What have you learned since people have started using your bot?

A lot! There are literally 1000 ways how a person can ask for a restaurant recommendation and trying to support that with natural language processing is hard. Based on this we decided to switch to more pre-defined text and using more GUI elements.

Also, people love to test the boundaries of a bot and eventually they want to break it. Hence it’s equally important to educate our users how to talk to a bot, as it is building a responsive bot.

Finally, the speed in which we were able to capture learnings and improve the experience based on real usage was incredible. As opposed to cross-platform app development, we can instantly ship updates to all of our users without any disturbance.

Tell us a little about yourself – is this your first bot? 

I’ve founded and sold a startup in the food tech space in the past but this is my first chatbot.

What do you have in store for Sure?

After we launched on Product Hunt and expanded Sure to 22 cities around the world 2 months ago, we joined the Just Eat food tech accelerator in London.

We’re currently working on bringing the Sure experience into group chats and making it even more contextual as we grow to become the ultimate concierge for everything when you’re out and about – from choosing a restaurant to ordering an Uber to get home from a bar.

Tell us about your recently launched Sure extension for Messenger

We know that the way we discover restaurants is often by asking one of our friends. But many times, choosing a place to go with your friends can turn into a frustrating argument. This was the main motivation for launching our latest feature, the Messenger Chat Extension. This allows all our user to take the Sure bot with them to any group chat on Messenger and instantly share our recommendations with their friends. With this, we’re hoping to put an end to the “Where should we eat?” ordeal.

Behind The Bot: Forksy’s Mike Ushakov

Here at the Spoon, we read about and try out new foodbots all the time. This is Behind the Bot, a series looking at the stories of people behind the technology.

The past year has seen a huge surge in interest in virtual assistants and bots. While much of the action in the food and smart home space has been with voice assistants like Alexa, some of the most interesting work is happening in chatbots.

In this week’s edition of Behind the Bot, we feature Forksy, a conversational assistant that helps users track their food consumption. I’ve been using Forksy for the past week and found it fairly intuitive way to track food consumption and less work than many of the food tracker apps available on the market.

I caught up with Mike Ushakov, the CEO of Forksy.  Ushakov, who sold his last startup to Russian search giant Yandex, has been working on Forksy since mid-2016.

How did you get the idea for Forksy?

My cofounder & CTO (Eugene Molodkin) and I were watching the food diaries market to find a suitable solution for ourselves to track foods and drinks and to eat healthily. We were amazed by the complexity of the current solutions: it takes a lot of effort to track foods via any popular food journaling app. We saw an opportunity for a new product here.

Why is a chatbot a better way to track calories and food consumption vs. other methods?

There are two factors:
1) You can speak to a chatbot in your natural language
2) You use the chat bot in the environment that is natural for you – messenger

Both of these factors solve one major UI/UX problem: most of the users are not ready to adapt to a new interface. So it is usually a huge barrier to learning a way to track foods in a freshly installed food tracking app. And there is no barrier in Forksy’s case: you just tell the bot what you are eating and drinking and she does the rest.

On which platforms is Forksy available?

We are on Facebook, Viber, Kik, and Telegram – so on every significant platform presented in the Western world.

Why did you decide to make a food-focused skill?

We are tech guys, I sold my previous company a year before we started this new one – so we so the problem (absence of useful food tracking apps) and now are trying to solve it.

What have you learned since people have started using your skill? 

We have 100 thousand users on different platforms. The major thing we learned is that when you create an app, you compete with other apps on the phone’s home screen. And when you create a bot, you compete with the people in the contact list in Messenger. So the competition is much more fierce – and you need to constantly engage the user to survive. It is a tricky thing to do, as there are no best practices to read. Everybody is reinventing the wheel, but it is one of the most interesting things to do now.

What is the biggest challenge for bot makers?

To explain the whole world what the bots are and how to use them. Now only a fraction of people (even among journalists) get it.

Bot discovery is a challenge. How are you going about getting people to learn about and try your bot?

We rely on traditional marketing ways (like SMM and paid marketing) as well as on the quality of the product. The good product spreads itself.

How does usage patterns look post first engagement?

We see two types of the users – kids and grown-ups. Most of the kids play with the bot once and then never come back – but the product is not relevant to them, it is just a talking toy.

Grown-ups, especially women, likely to stick with Forksy at least for several days and try all the features. Some of the users stay for a month or even several months. We didn’t expect that at all given the current immaturity of our product.

Forksy is not relevant for all of the people in the world, but she is relevant for those who want to count calories. So most of the people who want to lose weight return after the first usage.

Why did you choose a chatbot using Facebook Messenger vs. a spoken word skill like Alexa?

It is only about focus; there is no contradiction between text chatbots and voice assistants.
Messengers are more wide-spread platforms than systems like Alexa, that’s why we start with the Messengers. When Alexa audience becomes comparable to the one billion users of Messenger, then everybody will be building for Alexa.

It is relatively easy for us to support Alexa and we play to do it some day.

Tell us about yourself and your team.

Forksy is our first bot. It is my second company – I sold my first one 2.5 years ago.

My co-founder and CTO is Eugene Molodkin, he works with me on a different projects for the last seven years. He is an engineer with 10 years experience and a computer science degree. We have a small team of several other people who help us create the product. My co-founder and I were born in Russia, I currently live between Russia and Europe and the team around the world (Berlin, Tel-Aviv, etc.).

We are still bootstrapped.

What do you have in store for Forksy? 

We are going to do much more extensive analysis of users’ food diaries than we do today, and provide the users with AI-enhanced advice on nutrition in the different ways. Some of the upcoming features will be paid.

Behind The Bot: Cooking Competition Creator Michael Gyarmathy

Whether you’re looking for a recipe suggestion, wine pairing or just want to chat with a celebrity chef, you’re in luck: there’s a bot for that.

With bots of all flavors flooding the market, the food space is particularly ripe for innovation as enterprising coders and food entrepreneurs try their hand at creating that virtual sous chef or grocery shopping assistant.

Here at the Spoon, we read and try out new foodbots all the time. In doing our research, we started to wonder about the people behind the bots and the choices they made in bringing their bot to market.

So, we decided to ask them.

This is our first in an occasional Q&A series with the person behind the bot. This first bot-maker is Michael Gyarmathy, the creator of an Alexa Skill called Cooking Competition.

Cooking Competition is a super basic skill that suggests a changing array of ingredient suggestions for you to test out your cooking skills. I tried it out on my own rather than facing off against friends, so I can being uses as a daily inspirational to come up with a cook-from-scratch meal ideas as much as for a competition with friends.

Whether you use Cooking Competition for ingredient suggestions or as a way to test your cooking prowess against friends, you can get started here.

Here’s our Q&A with Michael Gyarmathy:

Where did you get the idea for your Cooking Competition?

This Alexa skill is inspired by cooking competition TV shows such as Food Network’s Chopped. The concept is simple: compete with your friends in a test of culinary skill by coming up with dishes that incorporate the special “basket ingredients” provided by Alexa.

 Why did you choose to use the Alexa Skill vs other platforms?
The Amazon Alexa platform intrigued me the most due to ease of development and distribution. Amazon’s developer documentation provides a great starter template and then leaves you build whatever you desire. From my experience, the review and publishing process is also very simple and straightforward.
 
What is unique about developing for voice interface vs. other AI platforms?
I think voice interfaces are extremely useful in the kitchen because often times both of my hands are tied up in whatever I’m cooking, and being able to control a device with my voice rather than touching a screen is a game-changer. The AI aspect of the Alexa platform is an added benefit and will continue to be leveraged more and more in applications as the barrier-to-entry for developers continues to lower.
 
Why a food-focused skill?
Aside from programming, a lot of my down time is spent in the kitchen with my wife trying out new recipes. Cooking is a huge hobby of mine, and I want to find ways to combine my passions for cutting-edge technology and delicious food.
 
Tell us about yourself (Is this your first bot, other apps/software, education)? 
This Alexa skill was my first experience in the world of voice-driven interfaces and AI applications. In my day job, I work as a Mobile Solutions Consultant for Credera, a management and technology consulting firm located in Dallas. Prior to that, I graduated with a Computer Science degree from Texas A&M University.
 
What do you have in store for Cooking Competition (other bot platforms, new features, etc)?
The Cooking Competition skill could be improved by storing previous user interactions to influence future responses to the user. I’d also be interested in adding links to more information about the random basket ingredients as part of the response card in the Alexa app in case the user is unfamiliar with one of the ingredients.

Why The Chatbot Interface Might Just Be The Smart Home Story of 2017

Voice interfaces are so 2016.

Not that Alexa and Google’s voice assistant won’t grow a bunch more in 2017, they will. But the reality is the smart home continues to evolve at a rapid clip, and one of the early trends I’ve noticed for 2017 is the emergence of the social messaging chatbot as a natural language interface for the smart home.

Credit Mark Zuckerberg for kicking off the trend in a big way at the end of 2016 when he debuted Jarvis, a personal growth project that the Facebook founder worked on for much of 2016. But Jarvis was more than just a skunkworks project, as the chatbot platform built into Messenger is gaining steam, including as an AI assistant for the smart home.

I recently used Facebook Messenger’s chatbot myself when I cooked steak with my Joule, and I was struck by how intuitive chat was as a command and interaction interface. While Joule is the first connected home device I know of to use the Messenger chatbot, I can certainly envision more devices that would work well with Messenger as the primary interface.

And if you’re more of a text message person than a Facebook Messenger user, don’t worry: text chatbots are coming your way as well.  As Lauren wrote this morning, a startup by the name of Unified Inbox is working with the likes of Bosch and Samsung to text-messaging based chatbots into the smart home as a way to work with their products. And while Yahoo’s text-messaging chatbot platform Captain is mainly focused on organizing communication with other family members, it’s not a stretch to imagine it as a control interface for our smart home.

While this trend is picking up speed, we should note that it’s not entirely new. Back in 2015, I wrote about how one of the biggest social messaging platforms in WeChat had started to integrate with smart home platform company Arrayent to utilize the messaging platform as an interface for products using Arrayent’s IoT platform.

While Alexa and other voice interfaces will no doubt continue their eye-popping growth this year, the reality is they are only one form of conversational interface for connected products. That’s why you can expect 2017 to be the year people starting talking about – and to – chatbots as a way to start controlling their things.

I Made Steak With Facebook Messenger. Here’s How It Went

We know that over half of Echos end up in the kitchen, making Amazon’s voice assistant Alexa a good option for those looking for a new-fangled way to help make food.

But what about Facebook Messenger? While we don’t have exact numbers on how many use Facebook’s communication app while in the kitchen, with over a billion downloads of the app in Google Play Store alone, my guess would be a lot.

Still, that doesn’t mean we think of Messenger as an interface to, well, our steak, but that’s exactly what ChefSteps thought when they announced they’d created a Facebook Messenger bot for the Joule.

I’d used Alexa in the past to cook with my Joule, and it worked well for things like starting a cook and checking water temperature, but I wanted to see how cooking with Facebook would go and to see if a bot of the non-voice variety was useful when preparing the nightly meal.

Here’s how it went.

First I went to the ChefSteps support page for using Messenger and tried to talk with my Joule, which I had inserted into the water with a nice ribeye. I was told I would first need to log into my ChefSteps account. Fair enough.

Once logged in, the ChefSteps Chatbot, which we’ll call Joule-bot for this post, reminded me of what I’d named it and gave a few clues about what it could do.

I decided to jump right and tell Joule-bot what I wanted to cook a steak. I got a pop-up message telling me a little about sous vide complete with a visual guide to doneness (a big focus for ChefSteps overall with their guided cooking approach for the Joule app).

As you can see above, the tone of the bot is casual but also informative. I like the ability to choose the length of cook with their visual doneness guide. This is an advantage over cooking with Alexa which (obviously) can’t show you how what a cook will look like as a voice bot.

Once I chose medium rare (you didn’t think I wanted a Trump Cook did you?), Joule-bot asked me a few more questions to understand how to go about cooking my ribeye.

 

Once it knew I was cooking fresh and how thick the steak was, it was able to set the temperature. As you can see, I had already started the Joule (with Alexa – meaning I technically had a battle of the bots over my evening meal), so it told me, in essence, my water was running a bit hot. The Joule, like other sous vide circulators, can adjust down as it lets the water cook and will then hold the temperature, which is what happened for my cook.

You can also see that Joule-bot told me that that it is still young and hasn’t fully matured, meaning it wouldn’t be able to send me notifications in Messenger about when things were done. This is where Joule’s native app has an advantage over the Joule-bot.

I decided I wasn’t done with Joule-bot, since I wanted to see if it could help me out with my ribeye prep and post-cook. I decided to ask it a few more questions and see how it responded.

When I asked it how to prepare steak, wondering if I could surface some of the same types of information that Joule app does with its cooking guides. While it didn’t give me the same, concise cooking guide I get within the Joule, it did give me a link which provides access to much of the same information on the ChefSteps website.

My next message confused Joule-bot a bit, mostly because I think of my language choice. I was trying to get Joule-bot to tell me something it had already done (2 hours of cook time) with a specific question about that. Instead, it guessed that I was trying to see when my Joule would ship by surfacing an FAQ question.

While the logic wasn’t perfect, I think the response was fine. Since Joule-bot lets the user give feedback, this will help refine the bot’s logic over time. It also gave me lots of options of what to do next, with links to the ChefSteps community forum, recipes and also the option to file a support ticket.

Conclusion

Overall, cooking with Facebook Messenger was an interesting – but for now limited – experience. Joule-bot allowed me to set temperature based on visual guidance, told me in a conversational voice when my meal would be done, and directed me to the information rich ChefSteps website when it didn’t have the answers.

What it didn’t do was provide notifications, a big difference which gives the Joule app an advantage for now.  Joule-bot also didn’t have the richness of information provided by the in-app cooking guides (though, as mentioned, it did send me links to the ChefSteps website).

Compared to Alexa, Joule-bot has an advantage in the type of the information it can provide, such as visual guides around doneness.  However, Alexa commands are just a little easier (what’s easier than talking?) and I could see how Alexa would be preferred over Joule-bot when I’m preparing food with my hands.

Lastly, it’s important to ask the question: is cooking with Facebook Messenger a good idea?For now, I would say the Joule app is a better experience, but over time a bot could have some advantages. Messenger’s conversation logic is very good, and those used to using chat as a way to interface with people may also find it also a good way to control their things (like the Joule). I also think as many of us tire of apps for every device, Messenger is a logical candidate to become that universal app, especially as bots become better.

Why don’t you subscribe to our free weekly newsletter to get great analysis like this in your inbox?

ChefSteps Launches Facebook Messenger Cooking Bot For Joule In Expanded AI Initiative

You ever wonder what the emoji is for “steak, medium rare?”

Me neither. But if ChefStefs has their way, we may know soon.

That’s because the company has just launched the ability to cook with its Joule sous vide machine using Facebook Messenger. The new capability is part of a broader “Conversational Cooking” initiative that incorporates natural language interfaces such as Amazon Alexa (ChefSteps launched their Alexa skill last fall) and now, more recently, the Facebook Messenger bot framework.

ChefSteps describes a vision of “Conversational Cooking” where “the kitchen of the future as a place where the tools are smart, the conversation is natural and lively, and the food is amazing. Where ingredients, recipes, and fellow cooks are only a text bubble — or a voice command — away.”

The company doesn’t plan on stopping with Alexa or Facebook Messenger, either.

According to the Medium post from ChefSteps, “Conversational Cooking isn’t about a single website; it’s about offering options that fit naturally into people’s lives. It’s about talking to them in a human way, through familiar interfaces. Hate Facebook? Control Joule with the app or Alexa — or the app and Alexa. We’ll be adding new services as fast as we can to create a seamless experience that works on your terms.”

The concept of AI-driven bots tailored for the smart home and the smart kitchen is one that is likely to gain steam in 2017. It was just last December when Mark Zuckerberg unveiled his own smart home AI called Jarvis, which also utilized the Facebook Messenger bot framework as a simple control and interaction layer.

So it looks like 2017’s AI invasion of the kitchen won’t just be about Alexa and Google Home. Facebook’s Messenger bot may have a little something to say to us as well.

And one of those things might just be telling us when our steak is a perfect medium rare.