Supercharge your chatbot with AWS conversational AI

Chatbots have become increasingly popular, allowing you to improve customer service with 24-hour assistance, increase customer engagement with immediate, relevant answers to customer questions, and optimize cost and productivity with automation.

From within our data science and engineering practice at Rackspace Technology, I regularly talk to clients who want to implement chatbots into their business. There really is no downside. It’s fairly easy to build an initial proof of concept chatbot using conversational AI services that can show the “powers that be” the benefit of having a chatbot on the frontline of your contact center, an FAQ bot for your clients to get quick responses to common questions, or a business intelligence bot for your business and IT stakeholders to retrieve insights by asking questions regarding day-to-day activities.

Benefits of AI-enabled chatbots

Some of the more complex benefits allow you to obtain valuable insights on your data, gain knowledge on your inventory and significantly improve user experience for your clients. Conversational AI in combination with other cloud AI services can expand your chatbot’s capabilities to verbally respond to users, translate text into their native language, understand the context of their questions and deliver personalized recommendations.

Enter Amazon Lex, an AWS service for building conversational interfaces into any application using voice and text. Amazon Lex provides the advanced deep learning functionalities of automatic speech recognition (ASR) for converting speech to text and natural language understanding (NLU) to recognize the intent of the text. Combined, these capabilities enable you to build applications with highly engaging user experiences and lifelike conversational interactions. With Amazon Lex, the same deep learning technologies that power Amazon Alexa are now available to any developer, enabling you to quickly and easily build sophisticated, natural language, conversational bots, known as “chatbots.”

In layman's terms, Amazon Lex is a conversational chatbot that you can interact with and receive automated responses from based on the questions asked. Amazon Lex is also backed by NLU and deep learning with very little machine learning expertise required, which allows the bot to continually learn over time. Yes, your bot will get smarter. It is also a fully managed service which means you don't have to worry about the underlying infrastructure, and it scales automatically. Not to mention you only pay for what you use with no upfront fees or commitments.

How chatbots are being used

We're noticing an upward trend of call centers adopting chatbots to remain competitive and increase efficiency, but there are so many other domains that need to get into the chatbot game — from finance and e-commerce, to travel, healthcare and real estate. If a chatbot isn't booking your appointments, assisting in medical diagnoses, handling your reservations or letting your users know about their bank balances or recent transactions, then the odds are you are spending more money doing this another, less-efficient way.

As a genuine fan of Amazon Lex, I believe the benefits are extraordinary. As a managed service, it's easy to use and relatively cheap from a running cost perspective. Plus, it places you within the AWS ecosystem, where you can seamlessly integrate to the entire AWS world.

Think of Amazon Lex as the tip of the iceberg with the 200+ other AWS services underneath the water, waiting and ready. It’s your gateway to previously unimagined capabilities. Build an AR/VR scene using a virtual host to talk to your users through the web or an AR/VR headset, backed by Amazon Lex and Lambda performing all the logic. Back your Lex bot with: Amazon Translate to allow you to translate text to another language; Amazon Comprehend to retrieve the sentiment of your users;  Amazon Personalize to provide personalized recommendations to your users; or Amazon Kendra for document search that enables your Lex bot to find a document containing a specific recipe and deliver it to your customer as a downloadable link.

This isn't even getting into the ability to integrate Lex into Amazon SageMaker for a full end-to-end machine learning platform on top of your bot or even something as simple as Lex accessing all of your vast amounts of data in your S3 data lake. This is where the true power of Amazon Lex comes into play.

I encourage you to give this service a try. If you’re looking for guidance on how best to leverage Amazon Lex for your business or you want to accelerate the implementation, let’s chat.