3 myths about chatbot design, debunked

3 myths about chatbot design, debunked

Were you unable to attend Transform 2022? Check out all the summits in our on-demand library now! Look here.

These days, artificial intelligence (AI) chatbots are everywhere on websites, SMS and social channels. Conversational AI-powered chatbots using natural language processing (NLP) help customers handle everything from product recommendations to ordering questions.

Businesses also love conversational AI chatbots: According to a recent Gartner report, by 2027 chatbots will become the primary customer service channel for about a quarter of organizations. Over half (54%) of survey respondents said they already use some form of chatbot, virtual customer assistant (VCA) or other conversational AI platform for customer-facing applications.

According to Susan Hura, head of design at Kore AI, chatbots are not omniscient virtual assistants living on a website ready to answer any question at a moment’s notice. While integrating a conversational AI-powered chatbot may seem quick and easy, there are complex intricacies under the hood. A chatbot’s design, she explained, plays a more strategic role than one might think and requires a huge amount of human input to create.

Designing the conversational AI experience

Orlando, Florida-based Kore AI was cited in Gartner’s 2022 Magic Quadrant for Enterprise Conversational AI Platforms as offering a “no-code platform for conversational AI in the broadest sense, crossing over into adjacent product categories with interface and process building capabilities.” Essentially, the company develops conversational bots for businesses across different channels, from traditional web chatbots and SMS bots to Facebook Messenger and WhatsApp bots and voice-activated bots.


MetaBeat 2022

MetaBeat will bring together thought leaders to provide guidance on how metaverse technology will transform the way all industries communicate and do business on October 4th in San Francisco, CA.

Register here

Hura joined the company in March to build out an expert design practice for the company.

“Even though it’s a do-it-yourself platform, for many of our enterprise-level customers, a team of experts comes in to help define the framework for the bot or this suite of bots they’re developing,” she said.

There are five conversation designers on her team who define what the bot says to the user and develop the structure of the conversation. In addition, she explained that there are seven natural language analysts that define how the bot listens and interprets what the user says.

“Both of these together really form the conversational experience that someone would have interacting with one of these robots,” she said.

Hura, who has a Ph.D. in linguistics and began working on speech technology while working at Bell Labs, which she noted, “…was literally because I was sitting next to visual designers working on a speech technology project.” Hura said there are many misconceptions about conversational AI chatbots. Against this backdrop are three myths that she says must be dispelled.

Myth 1: Conversational AI chatbots are “magic”.

Truth: Designing successful chatbots takes time and effort.

Hura said she still sees business customers surprised by which conversational AI chatbots can not do.

“I think it’s partly because there are still an awful lot of marketers and people in the media who portray conversational AI as if it’s magic,” she said. “As if just by designing a conversational bot, all your dreams will come true.”

But just like any other technology, organizations must invest time to teach the robots to do the things they want them to do.

“You would never expect a human to fill the role of a virtual assistant to just automatically know everything and have all the information they need,” she explained.

That’s where it’s important to realize that “understanding” is really a human word, she added. “I think when people hear the words ‘natural language understanding,’ they think the technology is based on meaning, when in fact it’s not.”

In fact, she explained, conversational AI technology is based on language. “The bot simply produces output based on the analysis of all the inputs you put into it,” she said. “The better structured the data, the more intelligent a bot will sound.”

Myth 2: Chatbots understand users

Truth: Chatbots need context.

Imagine a user is on a website interacting with a conversational AI chatbot. The user says, “it seems like there is a duplicate load on line three.” The truth is that ‘line three’ means nothing to a robot, Hura emphasized.

“The bot is sitting there on the website, but the bot has no understanding of what’s going on in the context of the user seeing it,” she said. “So people often have misaligned expectations around the context of use.”

So, for example, if a customer is shopping for an item and wants a product comparison, a bot needs to be trained not just with a product comparison chart, but with all the data that was used to build that chart.

“The bot is not going to be smarter than your website,” Hura explained. “The conversational AI-powered bot cannot answer a nuanced question if it requires more data than is available. It can only answer to the extent that you have provided the data.”

Chatbots also require the context of the conversation itself.

“Sometimes these perceptions come down to the robot’s ability to speak in a way that is aware of the context of the conversation itself,” she said.

For example, if the bot asked the user for some information like “What is your account number?” then the following question might be “What is your password?” If the bot asked “And your password?” instead, it would feel more natural, Hura said.

“That’s how a human would say it,” she explained. “The word ‘and’ also does a ton of work in the conversation – it indicates that I’ve heard your answer and is following up with another question, it feels like the bot is aware of what’s going on.”

Myth 3: Chatbots don’t need design

Truth: Conversational AI chatbot design is as important as UX product design.

Hura said chatbot design is about user experience (UX) design. “On my team, we practice something called user-centered design with an iterative process,” Hura said. “When we think about the framework for conversations between a bot and a user, the more we know about the user — who they are, what their expectations are, what their relationship with the company is — the better.”

The first thing the Hura team does is create a conversational style guide, similar to the style guides created when building a mobile app, website or software. “We define the sound and feel that we want this bot to have,” she explained. “It’s a fun and unique thing that defines the personality of the bot.”

A script defines what the bot says, while flowchart-type diagrams map out all the possible paths the bot can go down.

For example, for an application where the user calls to make a service appointment for their car. The company must collect the vehicle year, make and model.

“If the user says early in the conversation, ‘I need to take my Corolla in for an oil change,’ I don’t need to ask about the year, make and model because I already know that a Corolla is a Toyota,” she said. “But we build flow charts to make sure the robot has the right words to say in every possible situation we might encounter.”

Conversational AI builds customer relationships

Overall, Hura explained that conversations are ways people build and strengthen relationships – including with chatbots.

“We make judgments about whoever we’re talking to, more than just that they gave an accurate answer,” she said. “And we assign personality to the robot, even when we’re 100% sure it’s a bot.”

That’s why it’s so important to make sure conversational AI chatbots have the right design, she added.

“Organizations should take the time to control that and make sure the bots are speaking in a way that reflects your brand value,” she said.

VentureBeat’s mission will be a digital town square for technical decision makers to gain knowledge about transformative business technology and transactions. Learn more about membership.

Leave a Reply

Your email address will not be published.