Amazon Connect adds AI-powered updates to improve agent efficiency and chatbot design

Amazon Web Services Inc.’s cloud-based contact center service, Amazon Connect, is receiving major under-the-hood updates today aimed at improving the experience for call agents and customers.

Amazon Connect is an omnichannel cloud contact center service launched in 2017 that businesses can use to enable customer service and customer engagement. Customer service representatives can respond to customer phone calls or chat requests in the same way as if the contact center infrastructure was set up and managed on-premises.

With the launch of Amazon Connect Cases in preview today, agents have access to a new case management feature that allows them to more easily track customer cases, collaborate with other staff and solve their problems faster.

As Amazon explains, case management is one of the primary tasks of customer service operations. Customer issues regarding issues such as payments and billing, product defects and service changes often require multiple conversations with different people before being resolved. In such cases, customer service agents use case management tools to track these issues.

However, these tools add a lot of complexity to the contact center infrastructure stack. Additionally, case management tools aren’t always very helpful, as they force agents to waste time switching between multiple apps to look up details.

Amazon Connect Cases aims to solve this problem by automatically creating a new case the first time a customer calls. It then tracks all related calls, chats, and tasks and keeps them in one place, so agents have a quick understanding of the case at their fingertips.

Chatbots can also access case information. So when a customer needs to speak or chat with a human agent, Amazon Connect Cases automatically routes them to the most appropriate agent with relevant case information attached. Amazon said this helps improve the average handling time for each case and often leads to a first-contact resolution.

Meanwhile, Amazon said, the introduction of Amazon Connect Outbound Campaigns gives businesses a more cost-effective way to engage hundreds or even millions of customers every day. The service, generally available now, can be used to power marketing promotions, appointment reminders or upcoming delivery notifications without the need to integrate third-party tools. Contact center managers can schedule and initiate high-volume outbound communications by specifying the communication channel, contact list, and content to be delivered.

Amazon Connect Outbound Campaigns makes life easier with a predictive dialer that automatically calls customers on a list, with scope limitation based on agent availability. It also uses a machine learning model that can discern whether the person answering the call is a human or a voicemail greeting, which helps increase agent efficiency by only connecting them to a live customer.

Shawn Hatton, senior technology delivery manager at Accenture Plc, said his company helped set up an Amazon Connect contact center for a state Medicaid agency client to handle incoming calls and leaving health insurance registration. The agency needed a simple way to contact thousands of people about their health insurance and leveraged Amazon Connect outbound campaigns to do just that.

“Previously, each call center agent spent up to 17 hours a month manually dialing nearly 1,000 different phone numbers,” Hatton said. “With outbound campaigns, calls are placed automatically, increasing agents’ overall bandwidth and taking 80% less time to make the same number of calls.”

A final update involves the general availability of Amazon Lex Automated Chatbot Designer, which makes it easier for businesses to design and build chatbots trained on their own transcripts.

As Amazon explains, the training process for AI-powered chatbots can take weeks. Chatbots are trained to identify customer intent by listening to hours of recorded conversations and reading thousands of lines of chat transcripts.

Amazon Lex’s automated chatbot designer can speed up chatbot training times to hours instead of weeks, Amazon claims. Developers feed their transcripts into Lex, which can analyze thousands of lines in just hours and use them as the basis for an initial chatbot design.

The generated bot design can be focused on common intentions, related phrases, and fed with a list of information needed to resolve customer issues, such as the customer’s insurance policy number and claim type. Once this base is built, developers can iterate on the design, adapting various chatbot prompts and responses until they get the right solution.

Photo: guvo59/Pixabay

Show your support for our mission by joining our Cube Club and our Cube Event community of experts. Join the community that includes Amazon Web Services and CEO Andy Jassy, ​​Dell Technologies Founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many other luminaries and experts.

About Geraldine Higgins

Check Also

Trial captains set off to answer tough questions as suits hide out at Headingley | England v New Zealand 2022

A day after the third Test between England and New Zealand and Headingley could hardly …