Consider your company’s level of complexity and demands when choosing between phone tree and conversational designs
By Michele Masterson
Consider your company’s level of complexity and demands when choosing between phone tree and conversational designs
By Michele Masterson
Consider your company’s level of complexity and demands when choosing between phone tree and conversational designs
By Michele Masterson
Phone tree–based IVRs are still the norm for most SMBs. The reasoning? They work.
Thanks to virtual agents such as Siri and its challengers, conversational design is becoming more familiar.
Customers who call a contact center are often required to navigate an IVR phone tree with myriad menus before being placed on hold and eventually reaching a live agent. At some progressive companies, a more pruned conversational system enables customers to request help by simply speaking into the phone. With one problem and two solutions, companies have to ask which is best for them: a phone tree–designed system or a conversation-driven design?
How May I Help You?
The conversation-driven design, also known as the “How may I help you?” interface, is starting to uproot phone tree–designed IVRs. To be sure, the tried and true phone tree designs have been around for decades and are a known and sometimes good, sometimes not so good entity. With these systems, customers call into a contact center and navigate a menu of options similar to branches of a tree before they ever reach a live agent.
“Half the time, when you let people skip a bunch of steps in the phone tree, they’re not sure what to do and they press zero,” says Bill Meisel, president of TMA Associates and executive director of the Applied Voice Input Output Society. “Companies realize that [this design] frustrates the customer and that it also doesn’t solve the problem unless it’s a simple issue. Someone once described a classic phone tree IVR as feeling as if you’re pressing a button with your tongue.”
David Pelland, director of UX innovations and design at Genesys, says that phone trees are known as discrete recognition menus, whereas conversational design uses natural language to let callers say what they want in their own way.
“With phone trees, you’d have to press one or press two in the days before speech recognition,” Pelland says. “You’d call in and you’d get literally a tree, as if someone drew it on a board.”
Getting Schooled in Design
According to Dena Skrbina, senior director of solutions marketing at Nuance Enterprise Division, there are two types of phone trees—touchtone and speech, also known as directed dialogue. The entire concept of a phone tree, she says, is a series of menu choices, but both of these ask the caller a series of questions to determine why she is calling.
With a touchtone tree, a caller may get a menu that says, “For billing, press one.” Once the caller presses one for billing, she will be asked another set of questions.
The other type of tree involves directed dialogue technology, which has the same structure as a touchtone tree but allows the caller to speak his response. The menu might say something such as “Please tell us why you are calling,” and the caller might say something like “Account status.”
“You can repeat something that the prompt said, in which case you go down another level and…get a similar prompt,” Skrbina says. “Eventually, you’ll get to some self-service functionality or an agent who can handle the call.”
Directed dialogue, Skrbina explains, uses speech recognition, but it’s very directed. “If you think about the structure of these menus…they both use that same structure. However, one is more convenient than the other because it’s hands-free—users can listen to a prompt and speak their answers.”
The difference with conversational design is that it uses natural language. With natural language, callers can say the reason for their call in their own words. Instead of a very specific question that would take a caller down a defined path, the prompt might say something like “Hi, thanks for calling. How may I help you?” The caller then would describe in her own words what the issue is.
“Natural language understands that and gets you to the right place,” Skrbina says. “With a tree paradigm, you probably had to have been asked three or four questions to get you to the right place. With natural language, you condense the trees and provide a more natural experience.”
With a touchtone phone tree, there is also the issue of the zero-out rate, in which callers press zero right away when they get to a menu.
“That [zero-out rate] is about nineteen percent,” Skrbina says. “When you move into a more conversational interface, it drops by four percentage points. A four percent increase in the number of people who can potentially automate makes business sense, and we see companies move toward this.”
While conversational design can have more complex technical issues for deployment, it is far easier for customers to use, Skrbina points out.
Bill Scholz, president of AVIOS and speech consultancy NewSpeech, says that the conversational approach combines speech recognition, natural language, and dialogue management, which breaks down the steps involving the design process.
The system first asks callers to say what they want. That response is then processed by a speech recognizer. The output from the speech recognizer is subjected to natural language analysis, where it is examined for various concepts and rules, and, after that has been done, it goes to a dialogue manager, which tries to manage the interaction between the computer and the caller.
The dialogue manager identifies what tasks or requests that person is calling about, which gets passed to a task manager. Then it goes in the other direction. The task manager will either typically provide information, or have some kind of question, which goes back to the user.
The output from the task manager will then go to a response selection mechanism, determining what sort of response should be delivered to the caller. That goes to a natural language generator, which turns this into a string of words. Finally, a text-to-speech engine will render that to the caller.
If you don’t want to settle for one design or the other, there is an option of combining phone trees with conversational design, says Deborah Dahl, principal at Conversational Technologies, chair of the Multimodal Coordination Group, and cochair of the Hypertex-Coordination Group at the World Wide Web Consortium.
“You can start out by offering people a few common options, such as ‘Press one for customer service.’ Then [the system] could send you into a more conversational interaction,” Dahl explains.
If It’s Not Broken, Don’t Fix It
Early adopters of conversational design include airlines, financial services, telecommunication companies, and, increasingly, utilities, all companies that have cash at hand to deploy such a substantial overhaul of their IVR design.
“Those companies that have been using IVR the longest are those same companies doing the most innovation,” Skrbina says. “We’re seeing it more in utilities, which at one time didn’t have as much motivation to deliver great customer service,” but now consumers have more choices. “This is an incentive to improve the customer experience.”
Even with such conversational design advances, phone tree–based IVRs are still the norm for most SMBs. The reasoning? They work, Pelland says.
“For most companies, it actually solves their problems,” he says. “Most IVRs are small enough that they don’t have to ask you more than two or three questions and you can get through them. The bang for the buck [for conversational design] isn’t there.”
Indeed, another speed bump to conversational design’s adoption is that it can be expensive to implement and tune on an ongoing basis.
That doesn’t mean the little guys can’t play in the same sandbox as the big ones. Skrbina maintains that some of the smaller players can get into the conversational design game. “For medium to large-size businesses, it’s a no-brainer,” she says. “For the smaller companies, the trend is more that if you’re going to use speech, use it in a hosted model,” Skrbina says. “With a hosted speech model, you’re not going to necessarily have to procure the technology. You can actually share with other companies. In the market, we’re seeing a trend toward hosted speech.”
“Conversational [design] is growing, but it isn’t highly prevalent yet because it’s expensive to do, requires a certain degree of expertise, and is a system that must be tailored to fit your particular needs,” Scholz says.
Filling Buckets
Larger companies were the first adopters of conversational design because they not only have deep pockets but also more “buckets” to fill. Pelland explains that when he is advising clients about IVR design, he first determines the number of unique destinations, or buckets, for callers.
“The number of buckets tells me if you’re a candidate for natural language or not,” he says. The reasoning comes back to the high cost of implementation.
Pelland says that if a potential client had 150 destinations, for example, it would make more sense for natural language.
“For a pizza shop, it doesn’t make sense, but for a company like Sears, shaving ten or fifteen seconds off an agent’s time in having to transfer you all of a sudden looks really good, and the savings [in time] can offset the cost,” Pelland says. “You’re saving your callers from spending time on the phone having to navigate ten menus. Saving agent time plus saving caller time looks pretty good on a spreadsheet.”
“Conversational design sometimes works better than having a human agent who’s just a router,” Dahl says. “The system can be more accurate than a person. A human has to remember 500 different places, and that’s going to be hard for an operator to do accurately. If there’s turnover in the call center, that’s going to compound the problem.”
In another scenario, there may be only three options people can choose when they call in, but there could be 100 products. In that case, the complexity of the products could make a case for conversational design.
Skrbina also suggests that large companies were first adopters of conversational design because they have the most to gain in cost savings and customer satisfaction improvements when compared to transferring calls to live agents.
Conversational Design and Virtual Agents
Consumers may feel that conversational design is somewhat clunky and hard to get used to, but thanks to virtual agents such as Siri and its challengers (e.g., Evi, Robin, and Google Now), it’s becoming more familiar.
“[Customers] are beginning to know what to expect and what a service like Siri can and cannot do,” Skrbina says. “They’re taking in that knowledge without really understanding that they’re doing it and are now bringing it to the IVR. They are more effectively using conversational interfaces.”
Another advantage with conversational design, Meisel says, is that a personal assistant is always consistent. “You will always get the same answer [and] it will always handle things by company policy, so you sort of have the perfect agent that can keep improving.”
Is Conversational Design Right for You?
With this information in mind, how do you know if you should stay with your phone tree IVR or move up to a conversational system that will play not only into your bottom line, but also into customer satisfaction, which, of course, also plays into your bottom line? One caveat: If you decide to go the conversational route, beware that while the technology looks promising, not every painter is Picasso.
“I think people take shortcuts,” Pelland says. “This is like a high-performance-engine. You need to treat it right and take care of it.”
The number one step, experts say, is to examine your objectives to determine the complexity of your system.
“If you find your phone tree getting three or four levels deep, then you’re forced to say, ‘If you want these options repeated, press five,’” Meisel says. “Then you’re in trouble. You’re probably not creating a good experience, and you’ll have an angry customer by the time [he or she] gets to an agent. If your phone tree has gotten too deep and your customers are often getting long wait times, that justifies a conversational system.”
It’s also important to do a deep dive and collect data to better understand why your customers are calling and how they are expressing what they want. Only then can you determine whether or not your company is actually providing it.
“You must get the company that desires this technology to carefully articulate the scope of the problem that it’s trying to solve,” Scholz says. “Get the business to precisely define what the task is that they want callers to interact with. If it’s a very large or complex task, then the cost for doing so goes up precipitously. If it’s a fairly modest task, such as some banking applications, then that is reasonable to do and does not require extensive effort.”
Skrbina suggests that IVR design considerations take into account other departments in addition to the contact center, and maintains that companies are much more successful when marketing or branding is part of the project. “For a long time, IVRs were kind of stuck in the closet somewhere, and the people in customer service and IT would cobble these things together,” she says. “What we’re seeing today is the focus on customer experience. These are becoming more of a corporate initiative with marketing and branding teams.”
From a technical point of view, one of the things required to build a natural language system correctly is that companies understand what their callers are saying on the phone. Pelland says that when his team is working with a client, the team will typically put in a false front end to an IVR so that literally everyone who calls in hears “How may I help you?” “Customers will say what they want to do, and we collect that and save it on a hard drive.
“We can get a thousand utterances from customers saying, ‘I have a tech support problem,’ which can be ‘I need to speak to tech support,’ and all the different ways people can say ‘I have a problem.’ That’s captured, and you use the real-world data to build an engine,” he says.
Pelland acknowledges that a new conversational system may take time for customers to get used to, and they may be inconvenienced at first because they may face extra questions while the system is capturing data. Because of this initial discomfort, Pelland says that companies should not be tempted to rush into implementing a conversational system. “I’ve seen people try to shortcut that, and the end result is atrocious,” he says. “If someone calls in with something that the businesspeople didn’t think of and it doesn’t get recognized, you get a horrible experience.”
The Outlook for Conversational Design
While conversational design may still be in its infancy, Skrbina points out that it will also become a big differentiator for companies. Despite being in different verticals, companies are no longer comparing themselves on an apples-to-apples level, but on an apples-to-oranges level.
“What’s changed is how people view their competition,” she says. “It’s no longer the norm for credit card companies to compare [their service] to the service of other credit card companies. Because consumers have so many digital relationships, a credit card company now has to look at customer service in utilities or in an airline and has to strive to meet that bar [of service].”
To be sure, conversational design offers a host of benefits, and experts believe that the technology will become a necessity. “Any company that has a significant amount of customer interaction is going to need to go conversational,” Meisel says.
“Conversational design will be expected because you’re going to see a lot of competition between Apple, Google, and Microsoft that will call attention to the natural language area,” he says. “You can’t [serve] millions of people at once except through automation.” 
Staff Writer Michele Masterson can be reached at mmasterson@infotoday.com.