Chatting with artificial intelligence chatbot on computer

Introduction to chatbots using Amazon Lex

What is a conversational interface?

A conversational interface is an interface in which you can talk or write to in plain language.

Human beings and computers don’t speak the same language. So, to make that interaction possible, we rely on graphical user interfaces (GUIs). However, in order to use GUIs, users have to learn where they need to type, that a hamburger button is a menu and which buttons trigger an action. But as technology evolves and language recognition and processing improves, interactions with digital services will continue to become more intuitive, accessible and efficient using conversational interfaces.

Instead of communicating with a computer in its computer language, by clicking on icons and entering syntax specific commands, you can interact with it using human language by simply telling it what to do.

Conversational interfaces will replace graphical or command line interfaces, which allows people to talk using voice or chat with a text interface that uses natural language with computers.

Sample bot conversation

The image above displays sample bot conversations. [1]

Types of conversational interfaces

  • Basic bots: Inputs for basic bots are limited. The design of the interface is basic, allowing for simple commands and basic inputs.
  • Text based assistants: This is the type you usually experience when interacting with a bot through text. You simply type the word and provide the input. Depending on the quality of your input, the bot will provide you with an accurate answer.
  • Voice based assistants: Voice assistants such as Google Assistant and Amazon’s Echo are adopted by many shopping sites. Amazon’s assistant can help you to order products or add new ones to your wish list. While basic bots and text-based assistants leverage images and video to convey their message, voice assistants have the difficulty of only relying on voice. While voice is sufficient for some use cases like re-ordering a frequently purchased item, voice may not be a good interface for examining a new product or picking an item from a menu.

The benefits of using a conversational interface

  • Available 24/7: One of the biggest advantages of conversational interfaces is that they can be there for your customers at all hours. No matter the time of day, there is somebody there to answer the questions and concerns your potential clients may have.
  • Automated/saves time: Conversational interfaces help businesses automate simple repetitive tasks that would otherwise take a large amount of time.
  • Interactive: Conversational interfaces contact, invite and message the user, whereas traditional apps require the user to download and install them before use.
  • Instant responses: Conversational interfaces provide an instant response from the bot, improving the overall customer experience.

What is Amazon Lex?

Amazon Lex is a fully managed service for building conversational interfaces into any application using voice and text, including:

  • 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.
  • The ability to build sophisticated, natural language conversational bots quickly and easily.
  • Increased contact center productivity, automation and operational efficiencies across an enterprise.

With Amazon Lex, the same deep learning technologies that power Amazon Alexa are now available for any developer to use. With Amazon Lex you can build bots to increase contact center productivity, automate simple tasks and drive operational efficiencies across the enterprise.

Chatbot sample template

The image above displays how the Amazon Lex bot can be configured using a sample template.

Benefits of Amazon Lex

Some benefits of using Amazon Lex are:

Ease of use
Amazon Lex provides an easy-to-use console to guide you through the process of creating your own bot or conversational interface. All you have to do is supply a few example phrases and Amazon Lex builds a complete natural language model through which your user can interact using voice and text, providing them the ability to ask questions, get answers and complete sophisticated tasks.

One-click deployment
With Amazon Lex you can build, test and deploy your bot everywhere across all your channels and platforms. This also includes mobile web apps, chat services such as Facebook messenger, Slack and Twilio SMS. Amazon Lex is a fully managed service that automatically scales with usage, so you don’t need to worry about provisioning hardware and managing infrastructure to power your bot.

Seamless AWS integrations
Amazon Lex provides built in integration with AWS Lambda and CloudWatch. You can also integrate with Amazon Cognito for authentication, DynamoDB and many other services. You can take advantage of the power of the AWS platform for security, monitoring, user authentication, business logic, storage and mobile app development.

Cost effective
With Amazon Lex there are no upfront costs or minimum charges. You are charged only for the text or speech requests that are made. Amazon Lex’s pay-as-you-go pricing and low cost per request makes it a cost-effective way to build conversational interfaces anywhere. With the free tier, you can easily try Amazon Lex without any initial investment.

How we can help

As an AWS Advanced Tier Services Partner, Baker Tilly Digital can build new chatbots and can integrate chatbots into your organization’s existing applications. Once created, we teach you how to use it to help your organization become more efficient and achieve your business goals.

Check out the second article in this series, Developing powerful chatbots using Amazon Lex to learn more.

Woman analyzes data on tablet
Next up

Inflation increases present more opportunities for smart gift giving