AI/Watson

Chatbots help bridge the context gap in customer service

Share this post:

Meet Nadine.

Nadine finds unexpected charges on her phone bill and, boy, is she frustrated. The same thing happened last month, and she had to speak with three different agents before the problem finally went away. Now that it’s back, Nadine is considering a switch to another provider. She even tweets about it, complaining to thousands of followers. Then she sighs and opens the company’s customer service chat window.

The company’s customer service department has no idea what’s coming.

There is a context gap in customer service.

Unlike you and me, the agent who picks up Nadine’s case doesn’t know her story. He doesn’t know that the issue has happened before, how long it took to resolve and how Nadine feels about it. In other words, he has no context.

The billing issue itself is an honest mistake—one that can be remedied quickly. But first, the agent must understand what’s happening and why, which means Nadine has to recount the whole story, all the while getting more and more frustrated.

Do chatbots change the equation?

What if we tweaked the scenario slightly by making Nadine’s first point of contact a chatbot powered by cognitive computing? After all, more and more enterprises are using cognitive bots to scale up and bring costs down. And some are getting really good at understanding natural language, like IBM Watson.

But even if a bot was brilliantly scripted and tuned for pleasant interactions, it would still face the same obstacle a human faces—the context gap. After all, if a human agent doesn’t know who Nadine is and what she’s been through, how would a bot know?

Making intelligent chatbots (and humans) even smarter

“How a bot would know” is precisely what HelpSocial is working on. Our platform collects and embeds contextual information wherever the customer interaction happens, whether it’s with a chatbot, on social media or on the phone with a human agent. That means Nadine can get the kind of service that any of us would reasonably expect.

Chatbot: Good morning! How may I assist you today?

Nadine: My bill is wrong again.

Chatbot: I’m sorry to hear that, Nadine! I see that we had a similar problem last month. Let’s get that fixed right away and make sure it doesn’t happen again.

The HelpSocial platform helps the bot become truly intelligent by surfacing clues about the customer’s circumstances and state of mind. For example, the word “again” in “My bill is wrong again” speaks volumes. We make it so the chatbot knows exactly what “again” implies and how to handle the situation appropriately. In Nadine’s case, it means seamlessly passing the conversation to a highly experienced agent who can immediately resolve the issue and dispel the frustration.

The continuing evolution of customer service

When the seeds of HelpSocial were planted, we weren’t necessarily solving for the context problem. We were just an internal group at Rackspace Hosting trying it make it easier to manage customer service through social media channels. We built a web application with an open API on the back end so we could integrate our data and features with any system—and we wanted developers to run with it. But initially we didn’t expect the API to be the main attraction.

After spinning off from Rackspace, we saw enterprise organizations using the API to experiment with social media in contact centers and integrate information in new ways. We started to focus more on the platform, creating new ways to bring contextual customer data into our customers’ service conversations and making the API even more extensible. That pivot led us to IBM Watson technology and cognitive chatbots, which has helped drive continued innovation at HelpSocial.

Because we’re focused on improving the fundamental interactions between enterprise organizations and their customers, we have a compass for navigating forward. It’s easy to see that chatbots and cognitive computing are a big part of the future of customer service. The context gap is a huge problem across all channels of customer care. A more automated and contextualized customer experience is the key to helping all the Nadines in the world (and let’s face it—we’ve all been there!).

  

CEO & Co-Founder

More stories

How to make campus life better with AI technology

In many organizations, business intelligence is the exclusive province of IT specialists and business analysts. However, those of us at Michigan State University (MSU) have a different approach. At MSU’s Division of Residential and Hospitality Services (RHS), we put IBM Watson Analytics into the hands of our operations managers. Its ease of use gives them […]

Continue reading

Payment fraud prevention at a national payment switch

France has a long history as a pioneer in payment fraud prevention. It was the only nation that introduced Chip and PIN countrywide in 1992 [1]. This action made France the first all-smartcard country. And it reduced fraud in France to almost zero overnight. For decades. But criminals became more sophisticated and fraud losses returned. […]

Continue reading

How to build trust in AI with blockchain technology

Machine learning and AI are all about data. We give AI-powered systems massive amounts of data to ingest and analyze, and then we trust the results. But I want to know how we can ensure the integrity of those systems, from the algorithms to the data sources. Solving the AI data-integrity issue I believe the […]

Continue reading