Conversational AI as Considerations for a Solution to Delivers Great Customer Experience

Conversational AI is a complicated technology. Many aspects need to align to create the best solution for the best customer experiences, including Automatic Speech Recognition, Natural Language Processing, Dialog Management, Machine Learning, and more.

Conversational AI as Considerations for a Solution to Delivers Great Customer Experience
Conversational AI as Considerations for a Solution to Delivers Great Customer Experience

Learn about the basics of the technology, as well as the top considerations for a solution that delivers a great customer experience at scale.

Table of contents

Conversational AI Cheat Sheet
Conversational AI: What is it and how does it work?
How does it work?
Conversational AI at a glance
Conversational AI Solution: From simple to advanced
Chatbot
Virtual Customer Assistants
Which one is right for your business?

Conversational AI Cheat Sheet

Choosing the right solution for your business

Conversational AI has been instrumental in improving customer satisfaction, decreasing costs, and increasing revenue. However, Conversational AI applications vary in levels of complexity and can result in dramatically different end products, and thus different experiences, for the end-user.

With that said, before choosing a Conversational AI solution for your business, it is important to determine not only your business goals but also the experience you want to deliver to your customers. Our cheat sheet will help you better understand the solutions available today, and the experiences they deliver, so you can better evaluate which is the best for your brand.

Tractical and IDC both identify automated customer service as the number one use case for AI-enabled digital transformation. Source: Tractica (2019, Q4). Customer Service Virtual Digital Assistants; IDC (2019, Q4). Worldwide AI System Spend for Automated Customer Service Agents.

Conversational AI: What is it and how does it work?

Before diving into specific Conversational AI, it is important to understand exactly what Conversational AI is and how it works.

Conversational AI is the set of technologies behind automated messaging and speech-enabled applications that offer human-like interactions between computers and humans. It provides human-like communications by recognizing speech and text, understanding intent, deciphering different languages, and responding in a way that mimics human conversation.

Conversational AI applications incorporate context, personalization, and relevance within human to computer interaction. Conversational design is a key part of developing conversational AI applications that flow and sound natural.

Conversational AI: What is it and how does it work?
Conversational AI: What is it and how does it work?

How does it work?

Conversational AI uses various technologies such as Automatic Speech Recognition (ASR), Natural Language Processing (NLP), Dialog management, and Machine Learning to communicate with humans at a human level.

Conversational AI at a glance

ASR: Listening

The application receives information input from humans—either written text or spoken phrases. If the input is spoken, ASR, also known as voice recognition, makes sense of spoken words and translates them into machine-readable format—or text.

Natural Language Understanding: Comprehending

Application deciphers what text means by using Natural Language Understanding (NLU)—one part of Natural Language Processing (NLP)—to understand the intent behind the text.

Dialog Management: Forming response

Application forms the response based on its understanding of the text’s intent using Dialog Management.

Natural Language Generation: Offering response

Dialog management orchestrates responses and converts them into a human-understandable format using Natural Language Generation (NLG), which is the other part of NLP. Application either delivers the response in text, or uses speech synthesis, the artificial production of human speech, or text to speech to deliver the response over a voice modality.

Machine Learning: Learning

The application accepts corrections and learns from the experience to deliver a better response in future interactions. This is called machine or reinforced learning.

Conversational AI at a glance
Conversational AI at a glance

Conversational AI Solution: From simple to advanced

Applied Conversational AI solutions range in abilities and therefore offer different experiences. Thinking about what your brand wants to deliver is key in choosing the right application.

Chatbot

The simplest example of a Conversational AI application. FAQ bots, or what most of us know as chatbots, are basic answer and response machines that have popped up on the websites and mobile apps of many brands as a way to automate simple interactions between a brand and its consumers. Most chatbots do not use NLP or dialog management to offer dynamic responses or machine learning to improve over time.

  • The simplest example of Conversational AI
  • Basic answer and response machine
  • Does not use NLP, dialog management, or machine learning

Chatbot | CX: When interacting with chatbots, consumers must type the exact keywords required to receive the appropriate response. The conversation flow is controlled by the bot, and the flow breaks or gets stuck in a loop when the bot is unable to understand the customer’s intention. Chatbots often fail to maintain context over the course of a conversation and cannot understand customer intent in many situations. Consumers often feel like they are going around and around in circles to get questions answered or information needed. This can lead to wasted time on the consumer’s part and a frustrating experience with your brand.

Chatbot | Important considerations: Chatbots are limited to text channels, which are rarely the channel choice of consumers or operational spend for companies. Therefore the impact on your customer experience and financials could be minimal. This also limits your ability to scale across other channels and therefore can’t grow with you as you continue to expand your CX initiatives as they change and grow with your business.

Can I order 4 apples, please?

You got it. I’ve added 4 apples to your list.

Actually, sorry. I meant 4 oranges.

You got it. I’ve added 4 oranges and 4 apples to your list. What else would you like?

No, that’s wrong. I DON’T want apples.

Got it. You have 4 oranges and 4 apples in your list. What else would you like?

NO! IT’S WRONG!

Got it. You have 4 oranges and 4 apples in your list. What else would you like?

It’s easy to get confused between a personal virtual assistant and a virtual customer assistant. A personal virtual assistant is an application for personal use, such as smart speakers or a virtual assistant on your cell phone. You probably use this type of Conversational AI application at least once, if not multiple times, throughout the day. Virtual personal assistants—including Amazon Alexa, Apple’s Siri, and Google Home—use ASR and NLP, but have simple dialog management. Learn more about virtual customer assistants on the next page.

Virtual Customer Assistants

Virtual customer assistants, often referred to as Intelligent Virtual Assistants, are more advanced Conversational AI systems that serve a specific purpose and therefore are more specialized in dialog management. These applications can carry context from one interaction to the next which enhances the user experience.

Virtual Customer Assistants | CX: Virtual customer assistants, also known as virtual assistants or agents, are becoming increasingly popular as a way to provide customer service conversations at scale because they offer a more conversational and natural way for consumers to interact. Consumers are not limited to typing or speaking in a certain way or using specific words or text to solicit responses. The result is a more effective and productive interaction that mimics a conversation with a real human and an excellent CX.

  • Provide customer service conversations at scale
  • Not limited to typing or speaking in a certain way
  • More effective and productive interaction that mimics conversation

Virtual Customer Assistants | Important Considerations: Virtual customer assistants can be an excellent way to offer a consistent brand experience across channels that leads to more productive conversations with your customers. These applications can also scale across channels and easily grow with your business to meet new and changing business goals. They are designed to be a company’s best agent at scale and can be customized to be brand and industry-specific. It is important to note that the design of, and the process of refining and tuning the application, often varies from vendor to vendor, so it is important to work with a vendor who understands your needs.

Hello and welcome to Franklin Fruit. How can I help you today?

Hello—yes. I needed to update my order.

I can help you with that. What is your order number?

257876.

Great. I have your order. How can I help?

I can’t believe I ordered 4 apples. I don’t like them. Can you remove those from my cart?

Yes, I can help you with that. I have removed the 4 apples from your cart.

Great—can you tell me the new total?

Your new total is $34.67. Is there anything else I can help you with today?

Which one is right for your business?

As you can see, two main types of Conversational AI applications vary in terms of complexity and experience. The critical difference can come down to the vendor you choose. Just like applications, vendors differ in their type and area of expertise, scalability, and proven results. Make sure your decision-making process includes a vendor vetting process where you ask detailed questions about experience, design, and referenceable results to ensure your application works exactly the way you want your brand to be represented.

Source: Interactions

Published by Thomas Apel

, a dynamic and self-motivated information technology architect, with a thorough knowledge of all facets pertaining to system and network infrastructure design, implementation and administration. I enjoy the technical writing process and answering readers' comments included.