Meet the teams: Toni

The second team we would like you to meet is Team Toni! Klemens is founder and main developer of Toni! He, Kathi who is responsible for UX and marketing (and is not on the picture ) , and Scott, their mentor, make up Team Toni at the moment.

Please give us a short description of your chatbot:

Toni is a personal football buddy on Facebook Messenger. He gives you information on all the scores, the latest results, upcoming games and news on soccer. He can provide you with real-time information or round-ups of past games. With Toni.ai we are going to redefine fan engagement by creating virtual buddies that sports fans can engage with on the popular messaging platforms. This is not just limited to football.

Why should someone use your chatbot / What is the problem that you are solving?

The thing about football information is, that it requires a lot of time to get all the information you want and often it is not personalized. With Toni we offer you your personal assistant that gives you the information you are searching for directly in the channel you already know and use – Facebook Messenger. You don’t need to install an App or log-in at a website. For leagues, clubs, and players we’ll provide a platform for increasing fan engagement and interact with fans on a personal level.

How did you guys meet?

The idea behind Toni arose last year for the European Football Championship 2016 where we built the first prototype. We already gained a lot of users and media coverage there. This was the beginning of the project, and now we are developing Toni further to be a general football chatbot and Toni.ai as a fan engagement platform for sports leagues, clubs, and athletes. This is also where the other teammates entered. I wanted to also include more of the business and UX side into Team Toni and therefore expanded the team.

Why did you choose Elevate?

Because it’s awesome! The guys are really motivated and we have the feeling that they can really support us and push Toni to a highly successful level! ELEVATE was the perfect fit for us. We had our first MVP and were thinking about how to market it and how we are going to build a business around it – and this is exactly where ELEVATE stepped in to support us.

What are your expectations for the program?

We really hope to have the big players of the soccer industry engaged in Toni – the big clubs or betting companies! And we want to give Toni a unique personality and attract as much users as possible!

When and how was your first experience with a chatbot?

My first experience was a news bot. It was very nice to get information, but it was not really personal. That’s something we want to do better with Toni – we really want to personalize the content. The user should feel welcome and see Toni as a friend.

What would you recommend to applicants interested in ELEVATE batch #2?

Do it! If you think about applying – just apply! Have fresh ideas, find a good team and then you will get support from TheVentury and it will give your product a push.

Do you have any advice for peers interested in building a chatbot?

The chatbot scene is changing very fast. You can now create bots without needing any coding skills. If you are living in Vienna, there is a lot going on: there are monthly meetups in the bot scene, there are hackathons and so on.

And if you want to talk about bots, just get in touch with us!

 

Want to know more about Team Toni? Visit them on Facebook or check out their homepage!


Meet the teams: Selly

The first team we would like to introduce you to is our dynamic duo Viktor and Vincent from Team Selly. Vincent is responsible for product and technology development and Viktor enjoys working out the financials, operations and marketing.

Please give us a short description of your chatbot:

We want to make selling the stuff you don’t need straightforward and time efficient. With Selly, we will be the one-stop solution for everything you want to sell or get rid of by combining all existing solutions under one simple-to-use interface – a chatbot.

Why should someone use your chatbot / What is the problem that you are solving?

Selling your stuff is time-consuming and frustrating. And if you are lazy like us, you either have your stuff lying around at home or, eventually, you throw it out – which sucks. With Selly, you simply take a picture of the item you want to sell, get a price, accept it, the item gets picked up and you get your money!

How did you guys meet?

We met at the age of 11 and became friends on a school project. We have been creating stuff ever since – we started with T-shirt shops and created apps and games together.

Why did you choose ELEVATE?


For us, ELEVATE is really valuable because they help us with our execution. We are only a two-men team and not that experienced in building bots. Therefore, having experienced growth marketers and developers on our side is exactly what we need.

When and how was your first experience with a chatbot?

My first experience with a chatbot was with HiPoncho, the weather cat. At first, I was skeptical, but I still use it to this day and it’s actually very helpful – we want to achieve the same experience for Selly!

What would you recommend to applicants interested in ELEVATE batch #2?

Ask questions as much as possible – the guys from TheVentury will definitely appreciate that and give advice!

Do you have any advice for peers interested in building a chatbot?

Don’t build a chatbot for the sake of building it! Ignore the buzz around it and look at your options, and see if it’s a great fit with your product and target group – and only then go for it.

 

Want to know more about Team Selly? Visit them on Facebook or check out their homepage!


How we built the Austrian Airlines Chatbot

Austrian Airlines ChatbotThe idea to the Austrian Airlines Chatbot was born right after the announcement of Facebook opening up their Messenger API. To us it was crystal clear from the beginning: this is going to be huge! And because we already realized a rather big innovation project with Austrian Airlines (see flymeto.austrian.com) we approached their social media agency ambuzzador to partner with us once again to bring this innovation to Austrian.

Said and done. Austrian Airlines were very quick in realizing the huge potential and allowed us to start the project.

What should we do? Where to start?

There were some major decision to make in conceptualizing the Chatbot. First, there was the question which functionality we should provide. What is the scope of the bot? We quickly identified that a minimal viable bot (MVB) for an airline should:

  • be able to search for flights
  • provide excellent answers to the top 5 customer support questions
  • be able to handle other questions reasonably well
  • do small talk on a basic level

Keep in mind that this was the MVB specification. It was clear from the start onwards, that we wouldn't be able to handle 100% of the requests successfully. So we needed an additional option:

  • If the bot fails, hand the conversation over to a human agent for further processing

This system differs entirely from the setup that KLM is currently believed to operate on, which is: Let an AI make a suggestion and a human sign off on the message. While it is obvious that their system (for now) is more precise - because a human is still in the loop - the future potential makes our approach more powerful. Only in a solution like this one can fully materialize the potential of an AI, but keep the human capacities for edge cases and complicated requests.

Hello, who is speaking?

Now that we knew what to speak about, the next question was: who is speaking?

There are two main strategies here:
a) You create an avatar, and let that avatar speak
b) The brand speaks for itself
Both have their advantages and disadvantages and I leave that to another discussion, but in the end we opted for B with Austrian Airlines: the myAustrian Messenger Service was born. Interesting side note: The decision was made not to use the word bot in the name, because Austrian Airlines users aren’t accustomed to this term yet.

Ok great, but how do we speak?

So now that we clarified what to speak about and who is speaking, we arrived at the question: How do we speak?
Most companies have a set of rules for their Corporate Design - but now we are talking text. So you need a "non-visual branding guideline", which, in most cases, exceeds the guidelines in a Corporate Design handbook. And that is exactly where our partner ambuzzador comes in. They provided the domain specific knowledge for Austrian Airlines, which includes standard greetings like "Servus" or certain ways to communicate. This domain knowledge is always an important part of the personality of the bot. Because only the personality makes the experience something unique and hopefully outstanding.

MVC ≠ Bot

After clarifying all the personality and soft parts, we finally had the go for the hard parts - building the bot.
But soon we realized that we had a major problem: A classic MVC (Model View Controller) structure of software projects doesn't work!
What is your controller? - You only have 1 view (the Messenger API so to say). It was really hard for us to press the structure of a bot into this excellent model of building software. So at some point we gave up and did what every developer does: Rethink everything!
What we came up with is, IMHO, a clever system to structure big bot architecture: a lifecycle model.
Only in a lifecycle model I have the possibility to hand over messages from different packages to another to facilitate a structured processing of the input to the output.
The Austrian Airlines Bot therefore has 4 lifecycle modules:

  • Enhance
  • Understand
  • Knowledge
  • Decide

austrian-bot-lifecycle

Enhance

In this first model we aim to correct and “enhance” - duh - the user message. We convert payloads to objects, emojis to a readable format etc. This is also where you correct spelling and grammar mistakes, or add additional context information for the next module.

Understand

In the “understand” module we try to understand the user intent and extract entities we are working with. This is mainly done by the NLP/AI service api.ai, which was recently aquired by Google. We decided to go with api.ai because back then, when we did our market analysis, they were the ones we felt most comfortable with concerning the quality of their modeling (though they are expensive). In addition to this external service we had to work around a couple of glitches and specialties of the platform to correct and further customize the results with our own little NLP engine. This was necessary since a general AI/NLP provider can't handle all the cases we wanted.
Here is also the point in the software where we try to generate a first answer to the user.

Knowledge

In this module we aim to improve the result from the previous section even further - either by finding better answers in the knowledge base of Austrian or by simply enhancing the output by e.g. quick replies that are fed from the long term memory. The latter is especially powerful since it drastically increases customer satisfaction and speed. In this module we work a lot with different IBM Watson APIs (which are extremely powerful, #fanboy). Here we also decide whether the content should be enhanced with a web view (e.g. a date picker in a web view) or not.

Decide

Now that we have finished the lifecycle, it is time to decide. This module now looks at the different answers that the previous modules produced and tries to decide what the best way to present the information in the messenger platform is. Is it a carousel?, An image? Just an emoji? Or is text just fine?
What you see in your message window is the outcome of this decision.

We failed - happens - how do we recover?

As mentioned in the beginning, it was clear that the bot wouldn't be able handle 100% of all use cases. So it was important to define an exit case that would hand over to the excellent support staff of Austrian Airlines. This in turn creates a few problems with the bot dynamic. Since the bot would automatically answer to every message, we had to "silence" it in these situations. This, and waking it up again, are some of the finer processes that are crucial to ensure a good customer experience overall.

 

SUMMARY

Overall, we were really happy with the results of this short 3-month innovation sprint with Austrian Airlines and are incredibly excited about what’s to come. We recognize that the bot performance we deliver at the moment is not yet were we want it to be - but that is how innovation and early prototyping works. We are constantly improving the setup and the confidence the system produces and are currently seeing more than 1.5k messages daily.

 

Side Note: Vienna the City of Bots

One amazing side note here: Vienna's Bot Community. We are very proud to be located right at the center of bot activity in Europe. The City of Vienna was voted the most livable city in the world 8 consecutive times and now we are proud to say that we - as a community of bot developers, designers, writers and product owners - are the capital of bots in Europe too. Our monthly meetup is probably the biggest meetup in Europe and events like the ChatBotConf clearly establish our position. We (TheVentury) are excited to also launch Europe's first chatbot centered accelerator in Vienna. We hope to further foster sustainable growth for this technology in Vienna, the City of Bots and are inviting everyone to apply to our first batch that starts Feb 2017.

 

Bots regards,
Jakob from TheVentury