August 14, 2020

How AI models remove time-sucking tasks from your customer support team

AI is here to stay. But it doesn’t have to be intimidating or mysterious. 

At Forethought, we strongly believe that AI is going to improve the way that customer support teams predict and anticipate customer needs.

For instance, predicting the need of a ticket when it comes in your door can be the most resource-draining task. It sucks up valuable human capital to have an expert route them, and it hurts the customer experience to have them wait in a queue only to get re-routed again a few days later. 

So, what can AI do and how does it help your customers? To answer this question, we have to talk about training models. 

So, what is an AI model?

A model is a black box that you feed inputs into. As Deon Nicholas, our CEO, explained so eloquently, “It gobbles up the information.” When it comes out of the black box, that piece of information now has a label attached to it. 

In the case of customer support, we’re talking about tickets getting labeled based on all of the information in the tickets.

Forethought creates different models that identify the need of a ticket, categorizing and routing them with labels related to priority, language, skill, department, or resolution. 

Each category for those labels is a new model. 

How do you train a model?

Training a model is somewhat like teaching a child about animals. 

Let’s say you want to introduce a child to the world of fish. You could go to the pet store and buy a goldfish, and your child would be so happy! But that goldfish is just one example of a fish. 

If you want your child to be able to recognize lots of different types of fish, you’ll have to teach them about more types of fish. So you head to the aquarium where you teach the child about all the various sizes, colors, and types of fish. Before you know it, they’re pointing out fish you didn’t even know existed.

And just like that, you’ve taught (trained) a child (a model).

In a sense, we each have models in our brains for identifying fish. We’ve seen enough examples again and again, and now we’re able to identify them easily.

Similarly, you train an AI model by teaching it lots of previous human experiences to then identify what something new is, without the help of a human! 

For customer support, we do this with tickets, using historical knowledge to better predict the future.

What are the best ways to leverage AI models in customer experience?

For customer support, we use AI models to help us predict a ticket’s need and solve customer issues faster. By creating models based on past issues, tickets, and categorization, you can leverage your past customer experiences to make the future ones even better. 

Can you give some examples of what it would like to use AI models for customer support?

  1. You can catch escalations before they create chaos and hurt your business using a model that prioritizes tickets based on past escalations and ticket priority. 
  1. You can funnel out any unimportant tickets and spam from your queue before an agent ever has to look at them using a model that labels tickets as “spam” or “not spam.”
  1. You can simply route tickets to the right place the first time for resolution without having to bog down talented agents with that clerical work using a model that learns all the categories or departments where similar, historical tickets have been resolved.

Because we use actual historical knowledge to then predict the labels for new issues, we can achieve high accuracy. Additionally, because we work off of historical knowledge, our models are perfectly tailored to a customer support team’s business need. 

At Forethought, we built Triage to make it insanely easy to build AI models on top of your existing tickets. 

Are you ready to explore Forethought’s Triage tool or other products that will empower your teams with AI? Let’s chat.

Download Forethought's guide for navigating the evolving landscape of customer support for 2021 and beyond.

Get your copy