Chatbots: The Force Awakens?

This is a guest post by Ayesha Borker, Amazon Connect senior solution architect at AWS

A long time ago, in a galaxy far, far away. It was the time of self-service and the emergence of new entities called ‘chatbots’. Many sought this technology, and a few attempted to understand where it came from.  In addition to lightsabers and Force-wielding Jedi – Star Wars introduced the world to two memorable droids – R2D2 and C-3PO. The robotic odd couple played a key role in the Skywalker Saga and helped save the galaxy. The simplest definition of a bot (or robot) is a machine that performs tasks replacing human effort, it is the advent of artificial intelligence that is kicking up a storm as we find ourselves at the cusp of redefining machine history.

It is essential to understand that artificial intelligence is a vast concept that will impact various sectors in different ways, but it has definitely arrived in the customer service arena with natural language understanding in the form of chatbots. Certainly, chatbots have attracted huge interest, but amidst that fanfare, we see many losing a chance at the out on the critical element of bot design and how to use it for bringing out the best in their business. It’s also important to know what we should expect from these assistants and the ideal design protocol. Here are some key bot attributes to consider:

1. Complexity: It is important that the customer and bot relationship remains simple. This basically means not offering too much at a time for the customer to experiment with. That means not confusing the bot too much human behavior at first. It would be best to start with simple interactions, keeping the bot language concise and logical. As the AI improves over time, more complex features and services like predictive capabilities can be offered. A bot that could maintain my previous interactions and throw me suggestions or proactively address my queries would surely be a winner.

2. Purpose: Customer service bots exist to serve a purpose. They should cater to one segment/bunch of queries /services most frequently asked by one’s customers. Follow the rule of thumb of self-service – let the frequently asked questions be automated. While, it’s fun to ask a banking bot, “What’s the weather today?”, it may actually not serve any business purpose. It is always a good idea to have a focused bot that wins a customer’s trust than attempt to set up a magician that may end up becoming a joke! After all, the intent is to create customer stickiness and offer a valuable self-service medium.

3. Human Backup: A bot may not have an answer to all your questions. But, it is important to not leave your customer stranded here with abysmal error messages. I personally feel, as a Step 1, the bot should ‘dumb’ things down and prompt some cues if the customer is lost. And if nothing works, the customer should be able to reach out to an agent and have the context of the interaction kept intact. This way a customer experience is never abrupt. It is a common practice for IVRs, why not have it for bots as well?

4. Naming: I feel a bot should have a catchy name to give it a more human feel. It would ultimately represent the face of one’s business and a robust call flow along with a name can be the recipe for a trusted advisor.

5. Analytics: Full-fledged business intelligence may not be a must-have for day 1, but analytics are key to making sure the bot actually works and looking closely at the bot’s performance. Logging what users write and how the bots responded, and how users respond to the answers shortly after go-live should be mandatory, to avoid a bot’s failure.

The motive of a bot should be to make a user’s life easier and benefit a business. With the right technology and design, it should not be much easier than understanding R2D2.


Financial AI Startup Personetics Raises $85M

Amazon Web Service Opens Healthcare AI and Voice Startup Accelerator

People Prefer Virtual Assistants That Seem Happy: Study