Interview: Dr. Susan Hura, Design Director at

I recently sat down with Dr. Susan Hura, Design Director at, to discuss the bank work involved in developing an intuitive AI-backed conversational chatbot. It will also dispel some of the myths behind the development and introduction of a CAI-enabled chatbot into a company’s digital platform. Whether used out of the box or customized, the design of a chatbot plays a more strategic role than one might think and requires an immense amount of human intervention for its creation.

insideBIGDATA: What are the often overlooked backend intricacies and intricacies in programming a CAI-supported chatbot?

Dr. Susan Hura: Customers are often surprised by the amount of work that goes into developing these solutions, as people rarely take the time to truly understand the capabilities of Conversational AI (CAI). Often the media sells CAI as magic when it is not; there are complex behind-the-scenes processes that must be supported by conversation designers and natural language processing (NLP) analysts to create interactions that feel simple. Any response given by the bot, someone programmed it.

For example, machine learning (ML) plays a vital role in the development of a CAI chatbot. Machine learning is a technique that allows us to take a large set of user utterances and analyze the range of ways users ask questions about different topics. The algorithm ensures that the CAI bot will understand that “What is my account balance?” is the same intent as “Can I get my balance please?” based on similarity in how the user phrased the question. The tricky part is when the user asks in a completely different way. As human beings, it is clear that “How much do I have while checking?” means the same thing, but it’s not automatic for a bot – someone has to do the mapping to point out the similarity.

The reason behind this is that the bots do not speak English, or any other language for that matter. When someone says to a chatbot, “I think my credit card was stolen,” the bot may respond with a kind statement like, “I’m sorry to hear this. Let me help you lock your card so that no one else can use it.” At first glance, it may seem like the bot empathizes with the user’s experience, but in reality, this response was programmed into the solution by a designer The more data these experts collect, the easier it is to build a bot that can deliver a natural conversational experience despite its limitations.

insideBIGDATA: How smart are out-of-the-box chatbots? Are they truly intuitive right out of the box?

Dr. Susan Hura: Conversational AI is more advanced than I thought when I was studying it in college. That being said, CAI-enabled chatbots are very simple entities that require a lot of human intervention. Out of the box, these solutions may seem smarter than they actually are. Most organizations understand that setting up a chatbot takes extra time and help. But there is inevitably a time when the company will want the bot to perform a new task, and the solution will not be able to help it. The organization is frustrated because externally the bot can do all these other interesting and valuable tasks; why can’t it automatically do something new? Well, you haven’t specially trained him to adapt to these new functions. Organizations should treat their bot as a new employee. They would never tell a call center agent to suddenly pick up a new set of skills without proper coaching, so why would they assume their chatbot is capable of it? People think robots are much smarter than humans when in fact they are much less intelligent.

insideBIGDATA: What elements are crucial to creating a CAI chatbot that builds a brand’s reputation and improves a customer’s overall experience?

Dr. Susan Hura: It’s easy to believe that the CAI technology itself will ensure the success of a CAI chatbot, but the design of the conversation is really the most imperative element. The design ensures that the sound and feel of the bot instantiates brand values ​​and engages end users by creating trustworthy and frictionless experiences. Many people believe that conversation design is just about writing prompts that sound good, but really, it’s about making sure the bot meets the needs of end users. These elements are driving business results such as increased self-service rates and reduced operational expenses. There must be a compelling reason that users want to engage with these technologies and if the design is poor, they simply won’t use them.

About the interviewee

Dr. Susan Hura is a conversational user experience designer and strategist with over 35 years of experience in linguistics, user-centered design, and speech technologies. She is a design director at, a leading conversational AI software company, and has previously worked on IVR and voice UI implementations for companies such as Lucent. Bell Labs Technologies and Human Factors International; she also founded Banter Technology, and SpeechUsability. She holds a doctorate in linguistics from the University of Texas at Austin and a bachelor’s degree in linguistics from The Ohio State University.

Sign up for the free insideBIGDATA newsletter.

Join us on Twitter: @InsideBigData1 –

About Chris C. Hairston

Check Also

Alleged AMD Radeon RX 7900 XT PCB Design Surfaces Online

Igor Wallossek from Igorslab has shared what appears to be a board design of an …