Key concepts of Genesys Dialog Engine Bot Flows and Genesys Digital Bot Flows

Genesys Dialog Engine Bot Flows and Genesys Digital Bot Flows help you create bots through a natural language understanding (NLU) engine that can interpret and process information the customer provides as input. Before you begin configuring and using bots and bot flows in Architect, review and evaluate these key concepts to help you get started.

Understanding bots

A bot is a conversational method of communicating with customers. Bots are powered by natural language processing (NLU) and artificial intelligence (AI). You can build bots in Architect and then integrate them into Architect inbound call, chat, or message flows.

When you use bots to automate conversations, you can simplify and improve the customer journey:

• Increase NPS and reduce customer wait times by allowing the bot to deliver quick responses to user requests.
• Reduce agent handling time by allowing the bot to perform routine tasks such as determining a customer’s message.
• Increase the organization’s availability by providing service outside normal business hours and easily scaling assistance during peak times.
• Improve containment rates as you connect customers to the correct self-service process. Or, if the interaction requires a live agent, improve first contact resolution and transfer rates.

Key terms

Genesys Dialog Engine Bot Flows incorporate key concepts that help you build bots. Review this terminology before you begin: 

• Intents: Intents describe a goal or task that users wants to do. For example, order tacos or reserve a hotel room. The user interacts with the bot to resolve their intent. When creating bots, think about questions that customers might ask.
• Utterances: Utterances are sample training phrases that customers might use to describe what they want to do. For example, “Can I order a taco,” or “I want to book a room.” Think about what the customer says to convey their intent.
• Slots: Slots are the specific pieces of information from an utterance to help understand the user’s intent. They are the words or phrases required to fulfill the intent. For example, consider the utterance: “I want to book two rooms.” In this utterance, the bot identifies the slot as rooms required, and maps the slot to a number slot type. Slots are dynamic. You can create a single utterance with a slot, and the bot recognizes any slot in that same sentence. After the bot identifies a slot, it maps the slot to a slot type. 
• Slot types: Each slot maps to a slot type. Slot types help the bot define the information that the bot looks for when trying to find a slot in the utterance. Sometimes the slot and slot type are similar. You can have a slot called “taco filling,” and a slot type of “taco fillings.” Architect supports two slot types:
  • Built-in (for example, the slot “number of tacos” would be a built-in number slot type).
  • Custom (for example, the “taco filling” slot needs a custom slot type).
• Confirmations: Confirmations are messages sent by the bot to confirm that it understands user intent. For example, “OK, can I help you book a room?”