Artificial Intelligence as a Service

There are lots of written tutorials and online videos on this subject.

Yet many of them omit important details of the bot building process. These details may vary from one user to another and are difficult to describe in a unilateral fashion. Consequently it is easier for tutorial writers not to mention them at all. We try here to fill the gap and provide some additional clarity.

1. Creating Facebook app.

One of the first steps in building a Facebook Messenger bot is creating a Facebook App. It requires a business Facebook page. This might seem obvious to avid social users yet worth mentioning: a business Facebook page can only be created from a personal Facebook page. If you already have a business Facebook page move on to the next step. If you have a personal Facebook page go on and create a business page. If you are among the lucky ones that live without Facebook presence now is your chance to become like everybody else.

2. Getting SSL certificate.

Next you need to setup a webhook. Your web application is hosted on a web server and the webhook’s role is to establish connection between Facebook and your web application via your web server. In order for the webhook to work you need SSL certificate because Facebook supports only secure connections (HTTPS) to external web servers. So first, you need to purchase it. The costs change from one company to another but it is important to buy a reliable certificate otherwise Facebook might reject it. All major ISP companies offer SSL products. Second, you need to install it on your web server. The installation process can be tricky. Sometimes you can get technical help from the ISP company that sold you the certificate (as a rule of thumb, the bigger the brand the better their technical support is supposed to be. But the cost may be higher too). You can also rely on popular tools, such as keytool command utility, assuming you know how to use them. In any case, it might be a good idea to allocate several days, up to a week, for this step when planning your project.

3. Choosing the server environment.

Your options are (almost) unlimited. Many online tutorials use Heroku which is a cloud-based web application platform, but a simple Tomcat web server would suffice too. Your decisions should be based on your business requirements.  A lightweight server such as Tomcat is a good fit when it comes to web centric, user facing applications. If backend integration comes into play, a web application server should be considered.

Your choice of programming languages is also broad. PHP is one popular option, Java is another but the list by no means ends here. Your chatbot app communicates with Facebook using POST requests, so any language that supports web protocols will work. Again, make decisions having your business goals in mind.

Chatbots and assistant programs designed to support conversations with human users rely on natural language processing (NLP). This is a field of scientific research that aims at making computers understand the meaning of sentences in natural language. The algorithms developed by NLP researchers helped power first generation of virtual assistants such as Siri or Cortana. Now the same algorithms are made available to the developer community to help companies build their own specialized virtual assistants. Industry products that offer NLP capabilities based on these algorithms are often called AI engines.

The most powerful and advanced AI engines currently available on the market are (in no particular order): IBM Watson, Google DialogFlow, Microsoft LUIS, Amazon Lex.

All these engines use intents and entities as primary pnguistic identifies to convey the meaning of incoming sentences. All of them offer conversation flow capability. In other words, intents and entities help to understand what the incoming sentence is about. Once the incoming sentence is correctly identified you can use the engine to provide a reply. You can repeat these two steps a large number of times, thus creating a conversation, or dialog.

In terms of language processing ability and simplicity of user experience IBM Watson and Google DialogFlow are currently above the pack. Microsoft LUIS is okay too; still, keeping in mind that Microsoft are aggressively territorial and like when users stay within their ecosystem, it is most efficient to use LUIS together with other Microsoft products such as MS Bot Framework.

Using AI engine conversation flow to create dialogs makes building conversations a simple, almost intuitive, task, with no coding involved. On the flip side, using AI engine conversation flow limits your natural tendency to make conversations natural. The alternative, delegating the conversation flow to the business layer of your chatbot, adds richness and flexibility to your dialog but makes the process more comppcated as it now requires coding. Cannot sell a cow and drink the milk at the same time, can you?

Amazon Lex lacks the semantic sophistication of their competitors. One can say (somewhat metaphorically)  that IBM Watson was created by linguists and computer scientists while Amazon Lex was created by sales people. As a product it is well packaged and initially looks pleasing on the eye, but once you start digging deeper you notice the limitations. Also, Amazon traditionally excelled in voice recognition component (Amazon Alexa) and not necessarily in actual language processing.

The space of conversational AI is fluid and changes happen rapidly. The existing products are evolving continuously and a new generation of AI engines is in the process of being developed.