What is a chatbot?

Chatbots, a new way of serving customers

In recent years, chatbots have been perfected and made their way into day-to-day tasks related to customer service. They ask questions, they answer, and they converse to make our life easier, but are they really as effective as they seem? They offer many advantages, although there are still some problems to solve.

Chatbots are programmed to interpret the reason behind the conversation and to answer questions.

Uses and applications of chatbots

A chatbot is a software application based on Artificial Intelligence that can have a conversation in real time by text or voice. In the first instance, there are the text-based customer service chatbots found on banking, insurance, travel, catering, etc. websites. Then we have the famous voice-based virtual assistants —Siri, Irene, Cortana and Alexa— designed to try and make our lives easier by answering our questions.

And they're not magic, they're science. Chatbots are programmed to interpret the context of the conversation and answer questions using Artificial Intelligence tools such as Natural Language Processing (NLP), which enables them to understand us, or Machine Learning, with which they can automatically learn from each interaction.

Types of chatbots

Depending on the use they make of that Artificial Intelligence, chatbots can be one of six types:

Linear conversational chat

These are based on a decision-tree architecture and are not very smart. Their flow of answers is determined by a linear chain of stages, so they give automatic responses rather than establishing a fluid conversation.

Non-linear conversational chat

Thanks to Machine Learning and NLP, they can interpret the user's intentions and the context of the conversation in order to respond accurately. If a user makes a request, the bot will understand it and return a few options tailored to his or her requirement.

Hybrid conversational chat

A combination of both the above that enables fluid and personalised conversation with users. If the chatbot doesn't know how to answer a question, it immediately notifies a human agent to add the answer into its database.

Voice chat

There are chatbots that work with voice commands, such as Amazon's Alexa and Apple's Siri. How they work is simpler since they listen to voice commands and respond in the same way.

AI chat

Artificial intelligence chats simulate human conversations. This is made possible by natural language processing (NLP), base models and machine learning, which allow them to listen, process and understand our expressions to respond as naturally and as personably as possible.

Generative AI chat

Generative AI chatbots are similar to conventional AI chatbots, but go one step further. While AI chatbots focus on understanding language and generating responses that are as human as possible, generative AI is capable of creating content, such as images or videos. Deepfakes or chatbots such as OpenAI's ChatGPT are examples of this type of AI, which can generate images, stories, songs and more.

The ultimate virtual assistant

Although they seem like a recent invention, chatbots go back to the 1960s.Eliza was the first. This was a rudimentary software program created in the Artificial Intelligence (AI) laboratory at MIT. It could simulate a conversation by using a pattern comparison methodology. One thing that is certain is that the chat was more monologue than conversation.

Despite its limited functionality, Eliza fired the starting gun for a dizzying race that has led to today's chatbots, which are far more intelligent and sophisticated. This qualitative leap has been so great that many companies are adopting chatbots as a new, fast, efficient and profitable way to provide customer care services.

Today 62% of consumers would rather interact with an AI chatbot than a human and by 2030, with the upward trend of chatbots, this market is expected to be worth $27.3 B. So, what exactly is a chatbot?

SEE INFOGRAPHIC: Steps required to implement a chatbot [PDF] External link, opens in new window.

Advantages and disadvantages of an enterprise chatbot

The use of chatbots, is becoming more and more common and is gradually becoming a part of our daily lives, especially in the field of customer service, although not only in this field. Nowadays, virtual assistants are beginning to be used in companies to promote sales, retain customers and generate content of interest.

Chatbots have numerous advantages: 24/7 365 days a year availability, fast and efficient response, constant learning, cost savings, easy personalisation and even social media management! And the disadvantages? Although natural language processing is getting better, these tools don't capture certain characteristics of human language such as double meanings, sarcasm and moods, which can lead to customers getting frustrated. Also, many people, especially the elderly, reject these types of technological advances and there is the possibility that the system may fail mid-conversation, causing discomfort and mistrust in the user.

Differences between virtual agents and chatbots

The terms "chatbot" and "virtual assistant" are often confused, mainly because they are very similar in essence. However, there is a subtle difference between the two.

AI chatbots process language and generate responses that mimic human speech. If you ask an AI chatbot: "Where’s the Sagrada Familia?", it’s likely to answer that it’s in Barcelona, Spain, and to tell you a bit about the history of the cathedral.

A virtual assistant, however, combines AI language processing and intelligent search with robotic process automation (RPA). Its goal is to act on the user's request to minimise human intervention. So, if you ask the same question: "Where’s the Sagrada Familia?", it will not only tell you that it’s in Barcelona, Spain, but, depending on your location, it might send you a link with maps, flights or different options to get there from wherever you are.