3 chatbot design myths busted

Couldn’t attend Transform 2022? Discover all the summit sessions now in our on-demand library! Look here.

These days, artificial intelligence (AI) conversational chatbots are everywhere on websites, text messages, and social media. AI-backed conversational chatbots that use natural language processing (NLP) help customers manage 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. More than 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, design director at Kore.ai, chatbots are not all-knowing virtual assistants living on a website and ready to answer any questions at any time. While onboarding an AI-supported conversational chatbot might seem quick and easy, there are complex intricacies under the hood. The design of a chatbot, she explained, plays a more strategic role than one might think and requires an immense amount of human input for its creation.

Design 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 broader conversational AI , crossing 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-enabled bots.


MetaBeat 2022

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

register here

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

“While this is a DIY platform, for many of our enterprise-level customers there is a team of experts involved to help define the framework for the bot or that suite of bots. that they develop,” she said.

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

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

Hura, who has a Ph.D. in linguistics and started working in speech technology while working at Bell Labs, which she noted, “…was literally because I was sitting next to visual designers who were working on a speech technology project.” Hura said there are a lot of misconceptions about conversational AI chatbots. In this context, there are three myths that she believes need to be busted.

Myth 1: Conversational AI chatbots are “magical”

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

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

“I think it’s partly because there are still so many salespeople and people in the media who describe conversational AI as if it’s magic,” she said. “As if just by designing a chatbot, all your dreams would come true.”

However, like any other technology, organizations need to invest time in teaching bots to do what they want them to do.

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

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

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

Myth 2: Chatbots understand users

Truth: Chatbots need context.

Imagine a user is on a web page interacting with a conversational AI chatbot. User says, “Looks like there is double rate on line 3.” The truth is, “line three” means nothing to a bot, Hura pointed out.

“The bot sits on the website, but the bot doesn’t understand what’s happening in the context in which the user sees it,” she said. “So people often have the wrong expectations about the context of use.”

So, for example, if a customer buys an item and wants a product comparison, a bot will need to be trained not just with a product comparison table, but with all of the data that was used to create that table.

“The bot won’t be smarter than your website,” Hura explained. “The AI-backed chatbot 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’s aware of the context of the conversation itself,” she said.

For example, if the bot asks the user for information such as “What is your account number?” then the next 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 conversation – it indicates I heard your answer and I’m continuing with another question, I feel like the bot is aware of what’s going on .”

Myth 3: Chatbots don’t need a design

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

Hura said chatbot design is all about user experience (UX) design. “In my team, we practice what’s called user-centered design with an iterative process,” Hura said. “As we think about the framework of conversations between a bot and a user, the more we know about the user – who they are, what their expectations are, what their relationship is with the business – the better.”

The first thing the Hura team does is produce 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, unique thing that defines the personality of the bot.”

A script defines what the bot is saying, while flowchart-like diagrams plot 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 collect the year, make and model of the vehicle.

“If the user says at the start of 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 might encounter.”

Conversational AI strengthens customer relationships

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

“We make judgments about the person we’re talking to, more than just whether they’ve given a specific 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 should take the time to monitor this and ensure bots speak in a way that reflects your brand value,” she said.

VentureBeat’s mission is to be a digital public square for technical decision makers to learn about transformative enterprise technology and conduct transactions. Learn more about membership.

Comments are closed.