XIMNET — Digital Agency — an illustration of Kellie’s Castle located in Perak, Malaysia.
An illustration of Kellie’s Castle, Perak. Read about the story here.

5 common misconceptions about AI Chatbot

Let’s take a look at some popular myths about AI Chatbot and how we approach them

The first chatbot ever was developed by MIT professor Joseph Weizenbaum in the 1960s. It was called ELIZA.

Fast forward to 2016, we experienced a major wave of artificial data technology in chatbot design. Social media platforms such as Facebook took up this opportunity quickly by allowing developers to build AI chatbot as a service via Facebook Messenger.

What is AI Chatbot? In essence, an AI chatbot is a digital tool that converses with you. It responds by providing the information you need, offering remote support, making appointments and much more without involving humans in the interaction.

We see a significant rise of interest in the market from businesses of all sizes to implement this latest technology for various reasons. However, AI Chatbot is a relatively new field for businesses and many people have preconceived ideas about the technology that are not true at present time.

Are all AI Chatbot the same? Can AI Chatbot learn by itself? Let’s take some time to address them:

1. All chatbots use artificial intelligence (AI)

No, not all chatbots are using AI. While it is very tempting to assume so, not all implementation requires AI. Generally, they are split into two types:

Rule-based Chatbot

This implementation relies on preset rules. The chatbot can only perform effectively within the pre-defined environment. Open conversation is limited as it does not have the capacity to understand something beyond the world of if/then logic that is programmed in it. Often, a rule-based chatbot provides button options for users to interact instead of free text input. These chatbots demand rigidity and specificity.

An example of rule-based chatbot by KWSP / EPF

AI Chatbot

Unlike rule-based chatbot, AI chatbot utilises a range of Machine Learning (ML) components such as Natural Language Processing (NLP) to create a human-like interaction experience. NLP makes it possible for computers to read text, hear speech, interpret it, measure sentiment and determine which parts are important. AI also plays an important role in catching the context of a conversation and responding beyond keywords recognition. This advanced implementation can read into user patterns and create the best responses on the spot.

2. AI Chatbot can learn and improve by itself

While it is not entirely impossible, most businesses should instead focus on a hybrid implementation with training by a human.

The truth is, true machine learning requires massive amounts of data that very few businesses have. On top of that, machine learning is still a relatively expensive technology. Adopting an AI chatbot is a bit like adopting a pet. If you don’t know how to train a chatbot and take care of it properly.

Human training, also commonly known as supervised learning, should be incorporated to maintain the quality of AI Chatbot responses. Besides, you may not always like what it learns.

It is true that neural networks can learn on their own. But there is no solid and promising AI Chatbot software in the market that allows independent learning from past conversations without some human intervention. Continuous improvement is key so always spend time to identify areas where your AI chatbot needs more training will give you important insights about your business.

3. It is easy and fast to build an AI Chatbot

Yes, you can build an AI chatbot fast — it will fail fast too.

A good chatbot is more than just uploading a whole list of FAQs and letting it run on its own. A successful implementation includes strategic planning and process alignment. Businesses should spend time identifying the objectives and impact of incorporating AI Chatbot in their daily operations. Aim for long term benefits instead of meeting short term goals.

Do not forget to allocate time for testing and feedback too. Very often we underestimate the importance of thorough testing and do not allocate sufficient time to conduct user acceptance testing meaningfully. A poor quality AI Chatbot impacts your reputation so why not spend a little more time to get it right?

Seamless AI Chatbot implementation in Kuala Lumpur Convention Centre website

4. AI Chatbot is here to replace my human staff

While chatbots can take over basic repetitive questions or tasks, real people are needed to take up complex issues. Adding AI Chatbot into your operations is simply an initiative to provide better customer service. Unresolved cases by an AI Chatbot can always be passed on to a live agent to address.

Businesses should focus on providing meaningful roles for staff to on and grow in their career. With that, everyone grows and win together.

5. Building a multi-lingual AI Chatbot is as quick as copy, paste and go

While the quality of language translator has improved over the years, it may not be great at capturing cultural differences. A question can be asked in a different way in a different language so translating a conversation have to be more than merely pasting the English version into software to generate a direct translation.

A good multi-lingual AI Chatbot needs to understand how dialogues are formed in different languages. Some countries may appreciate direct questioning but others may not feel the same. Take time to understand the nuances of the language before you develop the conversation flow for your AI Chatbot.

PETRONAS Dagangan AI Chatbot by XTOPIA.IO

Final Thoughts

In this article, we are only highlighting a couple of popular misconceptions. We believe Artificial Intelligence will only get more exciting and be made available for more use cases. Perhaps in these challenges can be addressed in due time. For now, AI Chatbot is a valuable asset business should consider incorporating in day-to-day processes.

Here are some good reads on AI Chatbot and Conversational AI:

  1. Building Better Conversational Design for Your Chatbot
  2. How To Use Chatbots To Grow Your Business
  3. Does Your Company Really Need A Chatbot?

So, how do you intend to use it to meet your business goals today?

XIMNET is a digital solutions provider with two decades of track records specialising in web application development, AI Chatbot and system integration.

XIMNET is launching a brand new way of building AI Chatbot with XYAN. Get in touch with us to find out more.




Digital Agency in Malaysia | www.ximnet.com.my

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Robotics, So Far…

AI Is The New Internet

How Life 3.0 won’t take away your 2.0 life

Are Haunted NFTs The Next Big Thing?

IBM’s New AI — Project Debater Evolves to be an Invincible Debate Champion — Zerone Consulting

IBM’s Project Debater

AI Will Always Be Slaves, not Equals

Language and Motivation in Chatbots

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store


Digital Agency in Malaysia | www.ximnet.com.my

More from Medium

Use Case: Human-Informed AI for Video Editing

Is VR a Gimmick or the Future of Marketing? An Honest Discussion around VR and it’s Marketing Use

Why does AI Chatbot fail to deliver and how to make it right

XIMNET — Digital Agency — an illustration of the highest mountain in Malaysia, Mount Kinabalu

What Does The Future Hold For Natural Language Processing (NLP)?