How does one go about constructing an IVR system that can be used by people who don’t like IVR, whose needs aren’t met by IVR and who would rather talk to an actual person, preferably one with a reasonable command of the English language?

Simple: Design an IVR that knows when to gracefully bow out.

A precis on the IVR Deconstructed blog for a recent study by the University of Rochester and University of Illinois, titled “Robust Design and Control of Call Centers with Flexible IVR Systems,” mentions that the study argues that “businesses don’t have to choose between cost savings and service quality anymore -- they can design flexible IVR systems that satisfy all customers.”

And the way to do this, it concludes, is by designing an IVR system that knows when to hand a customer off to a non-IVR system.

Let’s give the much-maligned, frequently rightly so, IVR system its due. It’s saved companies millions and millions of dollars. It’s allowed you to get your bank balance at all hours of the day or night. And as the blog points out, it’s sure gotten a whole heck of a lot better in voice quality -- who’s nostalgic for the days of robotic humanoid voices? -- and understanding what you say, thanks to recent advances in voice recognition technology, and they’re a country mile better in the variety of calls they can handle.

Still, they’re not capable of handling all calls. No company interesting in staying in business entrusts an IVR with all of their customer service. The trick, as the study noted, is knowing when to hold ‘em and when to pass them off to a live agent.

The premise of the study, as summarized by the blog, is that “it is possible to design ?exible IVR systems whose service modes can be dynamically adjusted for each customer.”

Um, right. In other words, it’s possible to design IVR systems that have the opt-out hatch where you can escalate your call to a human? Yeah. Maybe we’re missing something here, but isn’t that fairly common today? We certainly expect that with the IVR systems we deal with. This is news?

“We propose robust dynamic routing policies to route customers to di?erent IVR service modes... When implemented in the way suggested…we show with numerical experiments that using a ?exible IVR system can decrease the total call center costs up to 10 percent compared to a system with a single IVR service type,” the study is quoted as saying.

The paper’s abstract itself spells out the issue a bit more: “In a typical call center equipped with an IVR system, customers are handled first by the IVR system... those customers whose service cannot be handled by the IVR system are sent to the second stage to be served by agents.”

Evidently the point of the paper is to help determine “the number of agents needed in the second stage as well as the proportion of customers that should be selected for each IVR service mode,” to find optimal staffing levels, which is fine and should be quite useful to the right people.

So bottom line, then: As good as IVR is, it’s still IVR, and there are just some things an IVR system can’t do.

Want to learn more about the latest in communications and technology? Then be sure to attend ITEXPO East 2012, taking place Jan. 31-Feb. 3 2012, in Miami, FL. ITEXPO (News - Alert) offers an educational program to help corporate decision makers select the right IP-based voice, video, fax and unified communications solutions to improve their operations. It's also where service providers learn how to profitably roll out the services their subscribers are clamoring for – and where resellers can learn about new growth opportunities. To register, click here.

Stay in touch with everything happening at ITEXPO. Follow us on Twitter.