Artificial Intelligence

Why Customer Service Chatbots Fail

Customer service chatbots are a white-hot topic nowadays. Vendor marketing drumbeat is loud, and they promise nothing short of eradicating world hunger with their chatbots! However, if you look beyond the hype, success stories are few and far between.

54% of online US consumers think that interactions with customer service chatbots will negatively impact the quality of their lives, per Forrester’s latest research, who predicts a chatbot backlash this year. A customer called the virtual assistant of a business he was dealing with a “virtual idiot”! How do you prevent your virtual assistant from suffering such ignominy? Here are 12 mistakes to avoid…

1. Doing too much

While a chatbot can become smarter over time, trying to do too much with it at the outset often leads to failure. It is best to limit its scope to a narrow set of use-cases and intents to get a quick win and then gain momentum. 

2. Passing the onus buck

When customers have a specific question, many chatbots just push back web pages or FAQs or documents instead of answering the question. It is like giving the entire haystack rather than finding and handing over the needle, which is what is expected from a chatbot.

3. Not understanding 

It is important to first understand the intent of the customer for fast time to answer. Except for the lonely soul or two out there, consumers are not looking to socialize with chatbots—they want quick answers. A good practice is to use human chat conversations, label the intent, and use machine learning to match the customer utterances to intents.

4. Do it my way

I was trying out a chatbot that had been touted as a success story only to have it repeatedly tell me to rephrase my question. I unloaded all the synonyms from a thesaurus and all the language variations I know (US, UK, etc.) to no avail! Step #3, combined with robust Natural language processing capability can help understand intent better.

5. Stopping with intent

Understanding intent is a good first step. Next, the chatbot needs to be able to converse and guide the customer to an answer, especially for the more complex queries. Look for a chatbot solution that is backed by AI reasoning to provide such guided, conversational assistance.

6. The bot switch

Some businesses are looking at creating a concierge bot and a set of specialist bots, where the concierge passes the baton to specialist bots if it is unable to answer a question. Bot-switching can be as painful as channel switching and can lead to poor customer experiences, especially if the specialist bots cannot resolve the customer query.

The answer is in implementing a smart chatbot, powered by a robust knowledge base and reasoning capabilities, that can escalate to human chat agents with full context ensuring the best possible customer experience. Another approach is to make the bot switch invisible to the customer. In either case, the customer experience should be at the front and center of the approach.

7. Can we start over?

Chatbots should be able to escalate to human agents, based on customer sentiment, customer value, customer situation, its own inability to resolve the issue, or a combination of these factors. And, it should do so with all the context intact so that the interaction with the human agent moves the conversation forward instead of starting over.

To see more ways to prevent chatbots from failing, visit: business2community.com

 

Post Your Comment




Leave another comment.

In order to post a comment, you must complete the fields indicated above.

Post Your Comment Close

Thank you for your comment.

Thank you for submitting your comment, your opinion is an important part of SandHill.com

Your comment has been submitted for review and will be posted to this article as soon as it is approved.

Back to Article