CXone Bot Builder

CXone Bot Builder enables you to create your own virtual agents, or bots, even if you have no coding knowledge or programming expertise. If you can carry on a conversation, you can create a working bot. These bots can do a wide variety of things, including:

• Answer common questions.
• Help a customer change their information in your system.
• Gather information before transferring to a live agent.

Conversational AI

CXone Bot Builder uses an approach called Conversational AI to design and train bots A software application that handles customer interactions in place of a live human agent.. This approach combines technologies that let computers:

• Recognize human language.
• Decipher different languages.
• Comprehend what is being said.
• Determine the right response.
• Respond in a way that mimics human conversation.

Traditional bots are completely scripted. A developer must try to account for every keyword a customer might use in a given scenario. Then the developer has to script a response for the bot for each of these keywords. As a result, these bots can be very time-consuming to set up and maintain.

When you create a bot with CXone Bot Builder, you train it using real conversations. Your bot retains context throughout an interaction. You give the bot the data it needs to respond, and it uses artificial intelligence to do so—and to get better at it over time.

Here's how the key concepts of Conversational AI work together in CXone Bot Builder.

Conversational Bot Concepts
Concept	Definition	Example
Message	Anything a contact says in an interaction, whether question or statement, written or spoken.	"I lost my password." "What is my balance?" "Are you a bot?"
Intent	What the contact wants to communicate or accomplish.	"I lost my password" has the intent of "reset password". "Hello" has the intent of "greeting".
Entity	Defined piece of information in a contact's message.	Person or product name, phone number, account number, location, and so on.
Slot	Entity extracted from a contact's message and saved for use in bot responses. Similar to a variable.	Creating a slot for contact name lets the bot use that name in responses during an interaction, making it more personal.
Rule	Used to define a bot's response to messages that don't change with context.	Single-turn interactions with fixed responses—What are your hours? What is your address? Conversation building blocks—Greetings, good-byes, thank yous and transitions; simple yes/no questions; and acknowledgments. CXone Bot Builder comes with default intents and rules for several of these, including greetings, handover Any contact message that should trigger transfer to a live agent requests, and more. FAQs Insults and classic bot challenges
Story	Used to train a bot to handle an interaction based on message intent and conversational context	In an interaction about a forgotten password, the bot would respond to, "How do I do that?" in one way. If the interaction were about creating a new account, the response would be quite different even though in both cases the contact is using the same words with the same intent – to get more information.
Action	Anything a bot says or does while handling an interaction.	Bot messages are one kind of action. Bots built with CXone Bot Builder can also send images or multimedia files, call an API, or handover the interaction to a live agent.

Key Facts About CXone Bot Builder

• CXone Bot Builder currently requires Digital First Omnichannel. Ask your CXone Account Representative about adding this product to your CXone environment.
• You can use bots built with CXone Bot Builder in any digital channel supported by Digital First Omnichannel. This includes live chat Agents and contacts interact on a real-time basis, CXone SMS Messaging, and all social Public social media interactions, such as on Facebook or Twitter and messaging Direct interactions using social media like Twitter DM, WhatsApp, or Facebook Messenger channels.
• To use CXone Bot Builder, you must enable the Chatbot permission in the DFO permissions. Chatbot is in the Settings Module detail permissions section.
• You can integrate CXone Bot Builder with APIs. For example, an integration with CXone Expert forms the solution CXone Answers. This lets your bot deliver answers pulled directly from your CXone Expert knowledge management center. For details, ask your CXone Account Representative.

CXone Bot Builder and Rich Content

Rich content like quick replies and multimedia can be sent through any channel, but it may not display to the customer correctly. For channels that don't support the delivery of rich content, your bot will use rich messaging fallback.

Use the following table to determine which channels will send which types of rich content. Any cells with a and any channels not specifically listed will use rich messaging fallback.

	Buttons	Cards	Multimedia*	Quick Replies	Rich Links	List Picker
Apple Messages for Business
DFO Chat
Facebook Messenger
Google Business Messaging
Twitter			images only
WhatsApp
Other Channels

*Multimedia file type and size restrictions apply:

• Images—PNG, JPG, GIF, or BMP format; 5 MB or smaller
• Videos—AVI, MPEG-4, or WEBM format; 200 MB or smaller
• Audio—MP3 format; 15 MB or smaller
• PDF, Microsoft Word, Excel, or Powerpoint—15MB or smaller

Tips for Getting the Most from CXone Bot Builder

• Build multiple bots A software application that handles customer interactions in place of a live human agent. for different use cases, channels, or audiences. You can then have them work together with live agents in your routing queues. Since CXone views your bot as a user entity, routing works the same way for a bot as for your real agents.

• Let bots handle your night shift to provide 24/7 customer service. Use the date and time filter in a routing queue to send incoming interactions to a bot overnight. The bot can either handle the interaction or route it to an agent for handling the next morning.

• Use sub-queues to drive a small percentage of traffic to start. Raise the percentage over time as the bot gets smarter and more capable of handling more use cases.

• Use sub-queues to split traffic between two different bots for A/B testing. This helps you validate which bot performs better.

• Take advantage of as many features as you can.

Any social media, social networking, and other technology sites, applications, or products referenced in this topic are the property of their respective owners.