This post was co-written with KYTC’s Tony Momenpour and Drew Clark.
Government departments and businesses operate contact centers to connect with their communities, allowing citizens and customers to call to make appointments, request services, and sometimes just ask a question. When there are more calls than agents can answer, callers are put on hold with a message like the following: “We are experiencing higher than normal call volumes. Your call is very important to us, please stay on the line and your call will be answered in the order it was received.”
Unless the music on hold is particularly good, callers don’t usually enjoy having to wait, as it’s a waste of time and money. Some contact centers play automated messages to encourage the caller to leave a voice message, visit the website, or call back later. These options are not satisfactory for callers who just want to ask an agent a question to get a quick answer.
One solution is to have enough trained agents available to handle all calls immediately, even during times of unusually high call volumes. This would eliminate wait times and ensure that callers receive prompt responses. The key to making this approach practical is to augment human agents with scalable AI-powered virtual agents that can address the needs of callers for at least some of the incoming calls. When a virtual agent successfully resolves a caller’s inquiry, the result is a happy caller, lower average wait times for all callers, and lower costs. Gartner Customer Service and Support Leaders Survey estimates that live channels such as phone and live chat cost an average of $8.01 per contact, while self-service channels cost about $0.10 per contact – a virtual agent can potentially save $ 7.91 (98%) for each call you successfully handle.
A virtual agent doesn’t have to handle all calls, and probably shouldn’t try; Some calls are likely to be handled better with a human touch, so a good virtual agent must know their own limitations and quickly transfer the caller to a human agent when necessary.
In this post, we share how the Kentucky Cabinet of Transportation (KYTC) Department of Vehicle Regulations (DVR) reduced call wait times and improved the customer experience with self-service virtual agents using Amazon Connect and Amazon Lex.
KYTC DVR Challenges
The KYTC DVR supports, assists, and provides information related to vehicle registration, driver’s licenses, and commercial vehicle credentials to nearly 5 million voters.
“In a recent survey of Kentuckians, more than 50% really wanted help without talking to someone,” says Drew Clark, business analyst and project manager at KYTC.
There were several challenges faced by the KYTC team that forced them to replace the existing system with Amazon Connect and Amazon Lex. The lack of flexibility in the existing customer support system prevented them from giving their customers the best user experience and continuing to innovate by introducing features like the ability to handle redundant inquiries via chat. Additionally, the introduction of federal REAL ID requirements in 2019 resulted in an increased volume of calls from drivers with questions. Call volumes increased further in 2020 when the COVID-19 pandemic struck and regional driver license offices closed. Callers experienced an average handle time of 5 minutes or more, an undesirable situation for both callers and DVR contact center professionals. Additionally, there was an over-reliance on the callback feature, resulting in a below average customer experience.
Solution Overview
To address these challenges, the KYTC team reviewed several contact center solutions and collaborated with the AWS ProServe team to implement a cloud-based contact center and virtual agent called Max. Currently, customers can interact with the contact center through voice and chat channels. The contact center is powered by Amazon Connect, and Max, the virtual agent, is powered by Amazon Lex and the AWS QnABot solution.
Amazon Connect routes some incoming calls to the virtual agent (Max) by identifying the caller’s number. Max uses Natural Language Processing (NLP) to find the best answer to a caller’s question from the DVR’s Q&A knowledge base, and responds to the caller using a natural synthesized voice and human-like (powered by Amazon Polly), supplemented where appropriate with an SMS text message containing links to web pages providing relevant detailed information. With Amazon Lex, the department was able to automate tasks like providing REAL ID information and renewing driver’s licenses or vehicle registrations. If the caller cannot find the desired answer, the call is transferred to a live agent.
The KYTC DVR reports that with the new system, they can handle equal or higher call volumes at a lower operating cost than the old system. Call response time has been reduced by 33%. They consistently see 90% of QnABot’s traffic routing through the self-service option on the website. The QnABot now handles close to 35% of incoming phone calls without the need for human intervention, during normal business hours and outside of business hours too! Additionally, agent training time was reduced from 4 weeks to 2 weeks due to Amazon Connect’s intuitive design and ease of use. DVR not only improved the customer and agent experience, but also avoided high upfront costs and lowered overall operating cost.
Amazon Lex and AWS QnABot
Amazon Lex is an AWS service for building conversational interfaces. You can use Amazon Lex to create trained self-service virtual agents for your contact center to automate a wide variety of calling experiences, such as claims, quotes, payments, purchases, appointments, and more.
AWS QnABot is an open source solution that uses Amazon Lex in conjunction with other AWS services to automate question answering use cases.
QnABot enables you to quickly deploy a conversational AI virtual agent to your contact centers, websites, and messaging channels, with no coding experience required. Configure curated answers to frequently asked questions using an integrated content management system that supports rich text and rich voice responses optimized for each channel. You can extend the solution’s knowledge base to include searching existing documents and web page content using Amazon Kendra. QnABot uses Amazon Translate to support user interaction in many languages.
Integrated user feedback and monitoring provide visibility into customer inquiries, concerns, and opinions. This allows you to fine-tune and enrich your content, effectively teaching your virtual agent to become smarter and smarter.
Conclusion
KYTC DVR Contact Center has achieved impressive improvements in customer experience and profitability by implementing an Amazon Connect cloud-based contact center, along with a virtual agent built using Amazon Lex and AWS QnABot solution from Open Source.
Curious to see if you can benefit from the same approaches that worked for KYTC DVR? Take a look at these short demo videos:
Try Amazon Lex or QnABot for yourself in your own AWS account. You can follow the steps in the deployment guide for automated deployment or explore the AWS QnABot Workshop.
We would love to hear from you. Let us know what you think in the comments section.
About the authors
Tony Momenpour is a systems consultant within the Kentucky Transportation Cabinet. He has worked for the Commonwealth of Kentucky for 19 years in various roles. His goal is to help the Commonwealth be able to provide its citizens with an excellent customer service experience.
Drew Clark is a business analyst/project manager for the Kentucky Cabinet of Transportation’s Office of Information Technology. She is focusing on system architecture, application platforms, and cabinet modernization. She has been with the Transportation Cabinet since 2016 working in various IT roles.
rajeev sharma is a Domain Lead – Contact Center in the AWS Data and Machine Learning team. Rajiv works with our clients to offer interactions through Amazon Connect and Amazon Lex.
Thomas Rindfuss is a Sr. Solutions Architect on the Amazon Lex team. He invents, develops, prototypes, and evangelizes new features and technical solutions for Language AI services that improve the customer experience and facilitate adoption.
Bob Strahan is a Principal Solutions Architect in the AWS Language AI Services team.
