Building an AI Powered Call-Center with AWS

The rise of artificial intelligence technologies enables organizations to adopt and improve self-service capabilities in contact center operations to create a more proactive, timely, and effective customer experience. Voice bots, or conversational interactive voice response systems (IVR), use natural language processing (NLP) to understand customers’ questions and provide relevant answers. Businesses can automate responses to frequently asked transactional questions by deploying bots that are available 24/7. As a result, customers benefit from reduced wait time and faster call resolution time, especially during peak hours.

In today’s blog, I’m going to share with you how we built an AI Powered Call-Center with Amazon Web Services for one of our global enterprise clients.

Client Reference Case

Our client is a global leader in independent testing, inspection, and certification services. For decades it has established its services worldwide, and they have been offering a broad range of services to various industries.
Behind that success there is a network of customer service representatives who are responsible for assisting customers to schedule, manage, cancel, and inquire about appointments for the different services.

With our help to leverage AWS technologies, Our client was able to build a seamless customer experience allowing customer service representatives to spend time with customers on more complex tasks while also providing users with a better experience through self-service powered by AI. Customer satisfaction increases while costs decrease since they’re consuming fewer connected minutes and maximizing agent utilization.

What are the benefits an AI Powered Call-center brings?

Some of the obvious benefits are:

The solution overview

The solution discussed in this blog enables customers to interact with a voice bot backed by a curated knowledge base naturally and conversationally. Customers can get answers to informational interactions, book appointments, and cancel appointments without having to wait for a human customer service representative, thereby improving resolution time and customer satisfaction. You can also implement the same bot directly as a web client, or embed it into an existing site as a chat widget, expanding touch points through multiple channels and increasing overall engagement with customers.

The solution contains the following major components:

Please note that we have excluded some other components from the diagram for simplicity.

Prerequisites

To get started, you need the following:

Implementation steps

To implement this solution, we’d walk through the following steps:

1. Design the bot workflows: What operations may the customers ask for, and what will happen for each? theoretically of course. For example, a “book an appointment” workflow may look like the following: A customer may ask to book an appointment, if so, we need to collect the customer’s basic information and ask for his preferred date and time for the appointment. Then the bot should check the availability of the requested timeslot, if it’s available it books it, otherwise, it apologizes and asks for an alternative slot. ..etc.



2. List down the needed endpoints for each workflow & ask the client to expose them securely: In the example above, for “book an appointment” we need two endpoints, the first one is to check the timeslot availability, and the other one is to book an appointment. This activity usually happens offline and it’s the responsibility of the client most of the time.
3. Write the needed lambda functions & deploy them. This can be written using any one of the supported runtimes.
4. Enable Amazon Lex & give it access to the lambda functions.
   
   Please note that every language supported by the Lex bot cannot have more than one lambda handler as of today.
5. Configure all the different intents & collect the user input where needed.
   
   
6. Create & configure an Amazon Connect instance.
7. Give the connect instance access to both Lex bot and lambda functions created previously.



8. Claim a phone number(s).
9. Create the needed contact flow(s) & leverage the Lex bot(s) created previously.



10. Link the contact flow(s) with the phone number(s).
11. Test, test, and test!

Conclusion

Combining Amazon Connect, and Amazon Lex allows your customer service representatives to spend time with your customers on more complex tasks while also providing users with a better experience through self-service powered by AI. Customer satisfaction increases all while costs decrease since you’re consuming fewer connected minutes and maximizing agent utilization.
Need to build an AI Powered Call-Center with AWS? We can help you with that, contact our team.