I built a chatbot in 2 hours to prove it’s useless, but here’s what I learned

Photo credit: John Jackson.

We spend about five hours on our smartphones every day, according to a study by Flurry. Not only is this statistic surprising in its own right but also about 65 percent of this time is spent on communication-related activities like being on social media, texting, emailing, and making phone calls. That’s three hours and 15 minutes. Every. Single. Day.

What it means is that the tables have turned at an acute angle. The mobile app that you are building for your kick-ass startup idea? It’s going to compete with millions of other apps for just 35 percent of the users’ daily attention. And don’t forget the discovery costs associated with it.

So, if you’re not going to make an app, what are you going to do? You have to set up your business, right? Most experts believe that the evolution of apps are chatbots that live inside apps. They extend the functionality of bigger platforms like Facebook or Telegram, and the user doesn’t need to install an extra app on their phone. This is a win-win situation for both parties—except for the developer, maybe. My personal suspicion in this play was two-fold:

• Building a bot is useless from a business perspective.
• Building bots is crazy tough from an engineering perspective.

To get to the bottom of this conundrum, I started to do some research. It took me around one month of passive reading, talking with experts, tinkering with tool kits, and procrastinating to finally code a functional bot in about two hours. This journey is my quest to find if both my suspicions were valid while having some fun doing so.

The journey begins

There’s a belief that inspiration often knocks at the door at odd hours, so one should stay awake to invite her in.

When I started writing this article, I knew nothing about bots. I had a superficial working knowledge of AI and how supervised learning worked in general, but to me, NLP was just an acronym that meant natural language processing. Half of the reasons why I started investigating chatbots was to learn more about the gaps in my knowledge of this particular play. Someone put it well: To curb your own personal ignorance is a joy of life cherished only by the most restless of minds.

My hunt for now was to address my first assumption about the bot industry ,  that is they don’t carry any business merit. After a bit of searching, I was able to find Botlist ,  a collection of a crazy number of bots. While browsing, my only aim was to guess and rationalize the developer’s decision to choose the bot platform over the app platform to solve their problem. How did making a bot make more business sense?

I found Mitsuku, of course, which was fun to talk to. Then Dr. AI seemed to be solving a good enough problem. Rightclick.io was good but a bit slow for my taste. Browsing through a lot of bots, from Hangman to TVakis, I noticed they seemed to be quite utilitarian in their approach. It seemed that the development is still in its infancy and the idea is yet to evolve. The good part was that I got enough ideas to implement my own chatbot seeing the problems that they were trying to solve.

I must confess that at some point, I felt like an art school undergrad roaming around the Louvre looking for inspiration. One question, however, continued to bug me.

Where is the killer app?

The bot industry is in its infancy right now and the object of the competition is to find the next killer app that will make chatbots mainstream. There are no reigning champions in the chatbot domain as of now. The whole industry is a level playing field.

It means that if the right idea struck, anyone could make the potential killer app.

I talked with a lot of people to investigate how far we really are into this future, and it was an educational ride just as I had imagined. The common consensus with the experts that I talked with put the timeframe to about two to five years until we see a really killer app for the chatbot platform. The technology is still evolving, so it is safe to say that even the best chatbots today can grow obsolete because of new announcements in AI and NLP research.

Grinding the bot

Salt and pepper