3 myths about chatbot design debunked

Today, conversational artificial intelligence (AI) chatbots are everywhere on websites, SMS and social channels. Conversational AI-powered chatbots using natural language processing (NLP) help customers with everything from product recommendations to order inquiries.

Companies also love AI chatbots for conversations: according to a recent Gartner report, chatbots will become the primary customer service channel for about a quarter of organizations by 2027. More than half (54%) of respondents said they already had some form of chatbotvirtual customer assistant (VCA) or other conversational AI platform for customer-facing applications.

According to Susan Hura, chief design officer at Kore.ai, chatbots are not all-knowing virtual assistants who live on a website and are ready to answer any question at a moment’s notice. While integrating an AI-powered chatbot may seem quick and easy, there are complex tricks under the hood. Chatbot design, she explained, plays a more strategic role than you might think and requires a tremendous amount of human input to create.

Designing the conversational AI experience

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

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

“While 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 set of bots they’re developing,” she said.

There are five conversation designers on her team who determine 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 who determine how the bot listens and interprets what the user is saying.

“Both of them together really make up the conversational experience someone would have interacting with one of these bots,” she said.

Hura, who has a Ph.D. in linguistics and began working in 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 background, there are three myths that she believes must be debunked.

Myth 1: Conversational AI chatbots are ‘magic’‘

Truth: It takes time and effort to design successful chatbots.

Hura said she still sees enterprise customers surprised by what conversational AI chatbots can not to do.

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

However, like any other technology, organizations must invest the time to teach the bots to do the things they want it to do.

“You would never expect that a person who took on the role of a virtual assistant would automatically know everything and have all the information he needed,” she explains.

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

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

Myth 2: Chatbots understand users

Truth: Chatbots need context.

Imagine a user interacting with a conversational AI chatbot on a web page. The user says “it looks like there’s a double write-off on line three.” The truth is that “rule three” means nothing to a bot, Hura emphasized.

“The bot is there on the website, but the bot has no idea what’s going on in the context the user sees it in,” she said. “So people often have wrong expectations about the context of use.”

For example, if a customer is looking for an item and wants a product comparison, a bot should be trained not just with a product comparison chart, but with all the data used to create that chart.

“The bot doesn’t get smarter than your website,” explains Hura. “The conversational AI-assisted 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 need the context of the conversation itself.

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

For example, if the bot has asked the user for information such as, “What is your account number?” then the next question may be “What is your password?” If the bot asked “And your password?” instead, it would feel more natural, Hura said.

“That’s how a person would say it,” she explained. “The word ‘and’ also does a lot of work in the conversation — it indicates that I’ve heard your answer and follow up on another question. It feels like the bot is aware of what’s happening.”

Myth 3: Chatbots don’t need design

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

Hura said chatbot design is all about user experience (UX) design. “In my team, we practice something called user-centric design with an iterative process,” Hura says. “As 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 team at Hura does is create a conversational style guide, similar to the style guides created when building a mobile app, website, or piece of software. “We define the sound and feel that we want this bot,” she explained. “It’s a fun and unique thing that defines the bot’s personality.”

A script defines what the bot says, while flowchart diagrams map out all the possible paths the bot could take.

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

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

Conversational AI builds customer relationships

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

“We judge who we talk to more than just that they gave an accurate answer,” she said. “And we assign a personality to bots 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 need to take the time to master that and make sure the bots speak in a way that reflects your brand equity,” she said.