Chatbots or conversational agents are so widespread that no one will be surprised by them anymore. The only thing that is amazing that’s how fast chatbots are getting smarter, more responsive, more useful. Sometimes, you don’t immediately realize that you have a conversation with a robot. So, what are chatbots? Simply, they are a communication interface that can interpret users’ questions and respond to them. Consequently, they simulate a conversation or interaction with a real person. They provide low-friction, low-barrier of accessing computational resources.

Conversational agents are not new. Historically, the first chatbot, called ELIZA, was created in 1966 at the MIT. The creator of ELIZA, Joseph Weizenbaum wanted to demonstrate that the communication between man and machine was superficial. So, ELIZA appeared as a parody of a non-directional psychotherapist in an initial psychiatric interview. The feature of such type of conversation is the ability to answer with a question. For example, ELIZA just reacted on a keyword “father” in the sentence “My father hates me.” and answered by “Who else in your family hates you?” Despite the parody purpose of ELIZA, it laid a foundation for the structures of chatbots like keywords, specific phrases, and pre programmed responses.

Then it was PARRY (1972), A.L.I.C.E. (1995), SmarterChild (2001). The high popularity growth of chatbots happened in 2010-2015, when it became possible to fully utilize the capabilities of machine learning, natural language processing (NLP), and convolutional neural networks techniques. That time, Siri, Google Now, Alexa, Cortana were created. These conversational agents are able to respond to voice commands, play music, perform internet searches, and, of course, provide a conversation.

Modern chatbots have a similar architecture. It consists of user interface that is used to give a user’s input (in natural language: text message or voice message) and receive an output of a chatbot generated in the dialog system. All the application logic is in dialog system box. In the dialog box, the user’s input is parsed, and progressive NLP techniques are able to identify the user intent and extract relevant entities. So, we use casual NLP pipeline. The difference is in the last step when chatbot should generate a response. Here we have two ways to get a response.

  1. The first one finds the best response from a library of predefined responses. Selecting the best response is based on a message and a whole context of conversation. Also, for selection we can use machine learning models or rule-based if-else conditional logic.
  2. The other way is to generate the answers and not always reply with one of the answers from a library. It is more difficult way where the answer is generated word by word, but it makes conversation more “natural”. When the user’s request is too complex, the chatbot can redirect the question to humans.

Nowadays, you can buy chatbots in bot-markets or find an open-source code and create a simple bot with low coding skills. Let’s see what the benefits chatbots can bring.

Benefits of Chatbots Using

Some of the advantages of conversational agents are obvious another needs some explanation. But what we can say for sure is that the chatbots is a cheap possibility to improve customer service whether they are AI based or not.

  • Chatbots provide their service 24/7/365. They are answering questions in real time without sleeping, weekends and holidays. But it doesn’t mean they “steal” humans’ jobs. Humans can focus on more complicated and more intelligent questions and pay more attention to more important issues.
  • Chatbots route conversations to the right specialists. Usually a company provides different services. Even simple bots without AI support helps customers reach right specialists as fast as possible.
  • Chatbots give higher satisfaction to the customers. A lot of people prefer to get personal support instead of reading long explanations. Chatbots with strong AI can provide realistic conversation and personalize future customer interactions. Since nearly 46 percent of people prefer messaging over phone and email, using of chatbots seems to be very promising.
  • Chatbots collect and analyze the questions your visitors have. Chatbots save conversations in order to further analysis of your customer’s needs.
  • Chatbots reduce customer’s waiting time. Customers get immediate answers to common questions in a chat window instead of waiting for the response by email or phone call.

How Chatbots Can Be Used?

Conversational agents are widely used. They are used as therapists, educators, lawyers. They are used in healthcare, banking, e-commerce, telecommunications, human resources. We will consider only few uses that chatbots can cover now.

  • Navigational chatbots. Customers sometimes are frustrated in site navigation: when they want to find a product page, FAQs, sales. Customers can ask their questions to a bot and receive the answer where they should click or direct link. Also, they can recommend relevant content to them. Some applications like Siri, Cortana, Alexa give the opportunity to use them as personal assistants.
  • Transactional bots. These bots carry out through transactional process within the context of conversation. They are very powerful in order to repeat customers’ purchases or actions.
  • Toys. Conversational toys are the example of the funny applications of chatbots. The set of rules and AI based conversational chatbot emulate a particular character and produce a storyline. For example, it was realized in Hello Barbie with a ToyTalk technology.

It is also important to mention the Tay chatbot as an example of the limitations of chatbots. It used tweets as a database in order to mimic speech and habits of teenage girl in 2016. But it was shut down after 16 hours of existence when it began to post inflammatory and offensive tweets.


In 2018, the chatbots market was worth $1.27 billion and is projected to reach $7.59 billion by 2024. People are very loyal to robots (according to Facebook, 1.4 billion used messenger applications and are rapidly willing to converse with a chatbot). Bots becoming smarter and begin to solve new problems. All this means that chatbots will boost the market growth in future.