Chatbots are, to be blunt, everywhere. It feels as if you can hardly visit a website these days without a bot asking how they can help you.

By Ryan Falkenberg, co-CEO of Clevva

It’s not just a matter of perception either. According to research from Gartner, chatbots will become a primary customer service channel for around a quarter of organisations by 2027.

Ubiquitous as chatbots are becoming, however, they still have a significant problem: aside from their inability to understand customer queries, many of them simply aren’t that helpful. Many of us know all too well how frustrating it can be to type multiple variations of a query into a chat box, only for the chatbot to keep returning irrelevant results (especially if there are no other avenues to contact the organisation in question).

Frustrating as it is that the typical chatbot is so poor at solving queries, it’s understandable. Fortunately, there is an approach that can make them much more useful.

 

The trouble with chatbots

When it first became clear that chatbots might be useful to the world of business (sometime in the mid-2010s), many organisations vastly overestimated what they’d be capable of. In their minds, they were getting a like-for-like replacement for human customer service agents. Chatbots, the thinking went, would be able to resolve customer queries completely unassisted.

In reality, what they got was more like a smart librarian. That is, the chatbot doesn’t know the answer itself, but knows where to fetch it from. Unfortunately, many of them are working with poorly constructed knowledge bases, meaning that the answers they provide tend to be generic and unhelpful (much like a librarian who only has access to out-of-date reference books).

It’s hardly surprising then that interactions with these chatbots can be so frustrating, especially once they go beyond simple requests such as “buy airtime” or “milk tart recipe”.

 

The service bot solution

Fortunately, there is a relatively simple solution when it comes to overcoming the limitations of chatbots. It involves adding a single additional step to clarify the intent of your query. Adding this step and doing so usefully requires the integration of service bots. A service bot is essentially a digital service expert that can help clarify your request, analyse your needs, identify the root cause of your problem, and recommend a solution.

That’s important for two reasons. The first is that it ensures that you start in the right place. So, for example, if you type “SSL Certificate” into a service bot, it can clarify whether you want to update it or if you want to get one. The more of these clarifications it goes through, the better its natural language understanding (NLU) gets, further improving its ability to answer queries.

The second is that you’re adding the capability to analyse a problem and come up with a relevant solution. Most chatbots don’t do that. They jump to a solution set immediately, which is not helpful if you don’t know what your problem is. With analysis, the resolutions the customer’s presented with are much more appropriate.

Additionally, the resulting actions can be processed with confidence because they’re more likely to be right. That in turn means that organisations are more willing to embrace automation and the benefits it brings.

 

Steps in the right direction

While many of today’s chatbots aren’t the customer service panacea organisations imagined they would be a few years ago, improvement is possible. With the help of service bots, most organisations can put themselves on the path to offering customers a Virtual Agent – one capable of resolving their queries first time.