We’re now in the final months of 2019. What have been the highs and lows so far? Have you moved the needle on CSAT scores and NPS? Has the customer experience fundamentally improved?

Many things to consider. But perhaps more importantly: did you get that chatbot up-and-running?

After all, Gartner made some bold predictions. In 2018, it was that over 50 percent of medium to large enterprises will have deployed them by 2020. Even before that, in 2011, they predicted 85 percent of all customer service interactions will be handled by chatbots and other automation.

Maybe you waited to do anything. The opinions had you spooked. The varying expectations led to some paralysis. It’s understandable. Emerging and rapidly-evolving technology is going to have both growing pains and naysayers.

The good news? With the remaining months in 2019 and some planning, you can be ready in early 2020 with a customer service chatbot that provides all its promised benefits while sidestepping the drawbacks.

Identify problems and goals

Businesses consider new technology to solve a problem. The first thing to do is understand what customer problems would be best solved by a chatbot. Most commonly, these are the higher volume, more common issues that bog down customer service.

In addition to selecting the types of issues to solve, set some success metrics. What percentage of the total service volume should be handled by the chatbot? For specific issues, what percentage will be handled by chatbot vs. other channels? How much faster should problems be solved by the chatbot vs. live agent interaction?

Don’t stop there. Be sure to consider customer satisfaction. As customers use the chatbot, get their feedback. Is it performing efficiently for them? Did they enjoy using it? Would they use it again?

Add some personality

While customers want fast, efficient answers, that doesn’t mean the experience must be dry and boring. One of the reasons customers might consider using the chatbot again would be its personality.

An easy place to start is by simply providing your chatbot with a name. Depending on your company or brand style, that could be playful or it might be more formal. Regardless, having a name takes some of the robotic nature out of the interaction.

What kind of voice should the chatbot have? Is it polite or more relaxed? An interaction style guide helps ensure the chatbot’s conversations are consistent and on-brand while avoiding anything that might be confusing or off-putting to customers.

Backed by solutions

Customers want answers fast. Much of the frustration cited in the articles above stems from chatbots being unable to solve problems quickly. It’s for this reason successful chatbots are those that focus on resolving a defined set of problems with proven solutions.

Solutions offered by chatbots can tap into other available self-service options. When many steps are involved, having the chatbot refer customers to a knowledge base article makes it easier for customers to perform them. Directing to automated solutions–forms to submit information or to perform other automation–is also ideal.

Teamed with humans

And just as a chatbot should be coded to solve a defined set of problems, it should also be programmed to throw in the towel when it doesn’t know an answer. Chatbots aren’t at the point yet to reason and troubleshoot as a human being can. For this reason, live customer service agents should be standing by and ready to step in. By not taking the customer in circles or asking unrelated or redundant questions, this will limit the customer feeling like their time is not being valued.

But it’s not enough to simply transfer the customer from robot to human. All of the interaction the customer has had with the chatbot–name or identifying information as well as a transcript of the interaction including any possible solutions offered–must be handed off to the customer service agent so that the customer needs not repeat already-shared information. It also gives the agent the background while preventing them from suggesting a resolution already proposed. When agents aren’t available due to high volumes or it’s outside business hours, the chatbot should offer to create a case for follow-up by a customer service agent at a later time.

Understanding language

Chatbots are designed to function based upon keywords and phrases used by customers. The marvel of language is the many ways in which humans can express themselves, and that can create challenges for chatbots–they struggle with nuance. But technology continues to improve in that area.

Modern chatbots use Natural Language Understanding (NLU) to provide a better conversational experience. NLU enables the chatbot to understand customer statements by using models to determine what the customer wants to do and to extract relevant values from their input. NLU also means the chatbot can offer a more natural and engaging conversation.

Even with NLU, be sure to periodically review chat transcripts of both successful and unsuccessful interactions. What were the words and phrases used? Use that information to improve the chatbot, both for solutions it addresses as well as to determine what solutions to add in the future.

A chatbot is in your future

Many companies are already benefitting from chatbots in customer service. They are taking more and more of the mundane work off the shoulders of customer service. In doing so, they are providing fast, efficient answers to customers around the clock.

Don’t get left behind! 2020 is the year to bring your chatbot to life in customer service. By selecting the right technology, taking a thoughtful approach, and imbuing your chatbot with the right traits, it will quickly become a productive and valuable member of the team.