Auto-crafting a message reply, and other GPT3 use cases | Support Hacks

Supporting customers will be (a bit) different soon. Deep dive into GPT3 use cases for Customer Service.

In this issue, I continue my exploration of GPT3 with a deep dive into some interesting use cases of this technology in Customer Service.

As I explained in my previous article, GPT3 is very good at spotting patterns and instructions from a snippet of text, called a prompt, then generate new text that continues that particular pattern or implements the given instructions.

Engineering the prompt for a given task is an important part of any GPT3 application. In the examples below, I adjusted the prompt to teach the API how to respond in three different situations: automatically compose a reply to a customer message from bullet points, add the “brand tone” to a given phrase, and summarizing a support ticket.

But let’s see go through each one of them in detail.

Writing is one of the main activities that Customer Support pros do every single day. Even the best and quickest typers, can spend a significant amount of time crafting a reply to a customer.

Because some of the writing is repetitive, most helpdesk platforms offer a way to save a reply and reuse it later on for a similar customer message.

Using saved replies might help but they bring a few additional problems:

Given that GPT3 is exceptional at producing text from a given prompt, I developed a pilot Zendesk app that takes the customer inquiry plus a short reply written with bullet points and generates a full reply that is ready to be sent to the customer.

The example above illustrates how, given a customer who wants to cancel an order, replies for two different situations are generated from bullet points: the order can be canceled and the order was dispatched already.

My bold prediction: saved replies will be replaced by AI soon.

Each business has its way of communicating with customers. A way that frequently has to be matched and scaled to large teams of customer service agents. A difficult task, given that each person has his or her way of communicating.

The pilot app illustrated below rephrases a given message to be more polite and appropriate for a customer service setting. However, the prompt can be adjusted to any brand tone: funnier, more somber, or anything in between.

Although not something you’d use when helping customers, this article shows the example of a chatbot that was fine-tuned to respond sarcastically. Most importantly, what it takes to adjust is only a handful of examples that teaches the AI how to phrase a response.

Reading and understanding a customer’s message is the first step to be done to address his or her inquiry. Many of such messages received by a customer support team are long, poorly written emails that require some time to decipher and comprehend.

This pilot app takes a long message from a customer and summarizes it by answering four preconfigured questions:

The questions to be answered from a message can be adjusted to include what customer service agents need to know to help him or her with the inquiry. In the example below, we keep the first two questions the same and replace the last two with one that tells the agents in a few words what the customer is asking.

What’s most remarkable is that to change the summary questions the only thing that you need to do is … change the questions. No need to construct a new training dataset or rebuild a model, as with other AI technologies. You don’t even need to provide one example of how to respond to those questions. This is the beauty of zero-shot learning at its best!

No matter how cool they are, none of these GPT3 use cases will matter if you don’t believe they could help your team and colleagues work better and more efficiently. That is why I’d love to hear your opinion. Do you think any of these could help? Please add as many details as you can.

There is no doubt that GPT3 represents an extraordinary breakthrough in Artificial Intelligence applied to Natural Language tasks. However, like any technology, it has its limitations. In the next issue, I will go through some of these limitations in detail.

Last but not least, ticket deflection (or customer self-help) is another important Customer Support use case where GPT3 can bring significant value. In the same next issue, I will describe how zero-shot learning powered by semantic search can be used out of the box to help customers find the answers they need.

I hope you enjoyed this issue and found it helpful. 😊

Sorin