Genesys Chatbots (CE31) for Genesys Engage cloud

From Genesys Documentation
Jump to: navigation, search
This topic is part of the manual Genesys Engage cloud Use Cases for version Current of Genesys Use Cases.
Read this topic for other versions:
Use chatbots to automate customer conversations and seamlessly hand over to a chat agent when needed.

Use Case Overview

Story and Business Context

The proliferation of digital channels has led to more demanding customer expectations and a drastic increase in the number of interactions that companies have to deal with when servicing their customers. Coupled with increased usage of AI for business applications, this has resulted in organizations implementing chatbots that can interact with customers to automate tasks and assist their queries on channels such as web, mobile, social, SMS, and messaging apps.

Chatbots can alleviate strain on contact center employees while improving the customer experience and controlling costs. Chatbots are always on and available, and can be handed over to an agent at any time if needed.

While chatbots can also be used by employees and for business optimization purposes, the remainder of this document refers to omnichannel bots in the context of customer engagement. The primary benefits of chatbots are to increase self-service success, deflect interactions from the contact center, and improve the customer experience. Benefits typically include:

Use Case Benefits*

Use Case Benefits Explanation
Improved First Contact Resolution Present a customer experience that is tailored to the individual based on who they are, why they might be interacting, and the status of the contact center
Improved Net Promoter Score Reduce the time required to address the customer request, handle off-hour requests, offer immediate options, and improve outcomes
Reduced Volume of Interactions Increase self-service interactions to reduce agent-assisted interactions for repetitive or common requests
*You can sort all use cases according to their stated benefits here: Sort by benefits

Summary

Genesys supports a “design once, deploy anywhere” concept for bots to enable organizations to provide a seamless customer experience across voice and digital channels. This use case, however, focuses on deploying a bot on web chat, mobile chat, Facebook Messenger, Apple Business Chat, WhatsApp, and/or SMS.

The chatbot supports or orchestrates the following capabilities:

  • Personalization – to tailor the experience based on context from the current interaction or from previous interactions
  • Natural Language Understanding – to derive intents and entities
  • Identification & Verification (ID&V) – to identify and verify the customer if required
  • Directed Dialog – to automate relevant business processes or provide information
  • Involve another NLU/AI platform (Amazon Lex or Google DialogFlow) – if it specializes in a particular topic
  • Handoff to an agent – to connect the customer to a live person with the full context of the interaction
  • Offer a chatbot survey depending on business context


Use Case Definition

Business Flow

When a customer interacts through a supported Genesys digital channel, a chatbot is initiated. The chatbot first attempts to use context to anticipate why the customer may be engaging and in turn provides personalized messages or options to resolve the query. If no personalization options exist, the chatbot asks the customer an open question, such as "How may I help?".

Once the customer responds, the chatbot tries to interpret the request to determine intent and then decide what to do next. For example, if the customer replies with “I want to check my balance”, the chatbot would first identify and verify them before showing their balance.

If intent is not established or understood, the chatbot passes the customer response to Knowledge Center, where it looks for suitable answers. If it finds an answer, it returns static information. If it doesn't, it presents a retry or max retries message.

Once the task is completed, the chatbot asks if the customer needs more help. The customer can respond by asking another question, requesting to chat with an advisor, or replying 'no'. If the customer replies with 'no', the chatbot can offer a survey based on context.

If the customer chooses to speak or chat with an agent and there is a long wait time or it is outside of business hours, then the chatbot can offer a callback option or present a suitable message.

The chatbot continues in this fashion, creating a conversational loop and building up context between itself and the customer to better solve their query.

The following diagram shows the business flow of the use case:

Business Flow Description

  1. A chat interaction is initiated (reactive or proactive) across a supported channel.
  2. The customer receives a standard welcome message from the chatbot.
  3. Customer information and/or context is retrieved from:
    • Customer profile information in UCS
    • Genesys User Data (e.g. Altocloud Segment or from the website passed by Genesys Widgets)
    • API call to third-party data source
  4. The customer receives a personalized message/menu or is handed over to an agent. Examples include:
    • Custom message or update: "Your next order is due to be delivered on Thursday before 12."
    • Most likely contact reason: "Do you want to find out about the loan application you have in progress?"
    • Tailored menu with most likely options: "Main menu: you can choose Balance, Payments, or TopUps."
    • Customer is handed over directly to an agent because they owe an outstanding balance.
    • If the customer is not handed over to an agent, the customer could end their chat, confirm the contact reason, or continue.
  5. Assuming the customer has moved on from the Personalization stage, the chatbot asks an open-ended question like: “How may I help you?” to determine intent and capture the customer's response.
  6. The customer's response is then sent to Dialog Engine (or, optionally, a supported third-party NLU engine). [BL1-BL2]
    • If intent and entities are returned, the conversation moves to the correct point in the interaction flow, which could be within one of the following sub-flows (or microapps):
      • Identification & Verification
      • Automated business process (such as payment collection microapp)
      • Handoff to live agent
    • If intent and entities are not returned and the customer has Genesys Knowledge Center, the system passes the raw utterance to Knowledge Center to look for a result.
    • If a relevant knowledge article is found, the results are shown to the customer and the customer moves to the next step.
    • If a relevant knowledge article is not found, the chatbot returns a message like: "Sorry, we didn’t find any results. Please enter another query or reply AGENT for live assistance."
    • If intent and entities are not returned and the customer does not have Genesys Knowledge Center, the chatbot returns a retry message like: "Sorry, we didn’t understand your question. Please ask another question or reply AGENT for live assistance."
  7. Upon completion of a task, the chatbot asks a follow-up question like: "Is there anything else I can help you with?"
    • If the customer responds “yes”, they're brought back to Step 5: "How may I help you?”.
    • If the customer responds “no”, the chatbot decides whether or not to offer them a survey (see step 8).
    • If the customer responds with a more advanced answer, the response is sent to Dialog Engine (or, optionally, a supported third-party NLU engine) to determine intent and entities for further processing.
  8. Customer information and/or context is retrieved to determine whether to offer a survey. [BL3]
    • If a survey is to be offered, the chatbot continues to the step 9.
    • If no survey is to be offered, the chatbot shows a goodbye message and ends.
  9. The chatbot asks the customer: "Would you like to participate in our survey?"
    • If the customer answers "yes", then they continue to the next step and engage in a survey.
    • If the customer answers "no", then they are shown a goodbye message and the chatbot ends.
  10. The survey is executed using the Designer survey microapp.
    • Optional: If the survey results meet a certain criteria based on the configured evaluation parameters, a specific action can be taken. For example, if the customer provides a negative response, they can be routed to a live agent.

Business and Distribution Logic

Business Logic

BL1: Agent Handoff:The customer can ask to be connected to an available agent. At that point the chatbot is disconnected and the chat transcript (excluding sensitive data) is displayed in the agent desktop. Other context can also be displayed as Case Data.

BL2: Retries:The number of retries for self-service tasks and questions can be configured by a business user. Upon maximum retries the dialog can be configured to present a message or hand off to an agent.

BL3: Survey:The customer can determine whether to address a survey or not. This can be based on:

  • Customer profile information in UCS
  • API call to third-party data source
  • Logic defined in Designer


Distribution Logic

When the conversation is handed over to a live agent, the interaction moves to one of these use cases, depending on the channel the customer is using:


Use Case Requirements

Customer Interface Requirements

Genesys Widgets are required to support out-of-the-box rich messaging capabilities for chat.

Agent Desktop Requirements

Are handled as part of channel-specific use cases:

Chat transcript between customer and chatbot is populated in the chat interaction window in the agent desktop.

Reporting

Real-time Reporting

Real-time reporting includes:

  • Agent Group capacity for chat interactions to define whether or not to offer escalation to customer service
  • Current Chat interactions waiting in the system
  • Total Chat interactions (self-service vs assisted service)
  • Agent Group Status
  • Queue/tenant-related stats definitions have queue names that are hardcoded

Historical Reporting

Currently, no chatbot specific historical reports are available out of the box on Genesys Engage cloud. Standard historical reports for chat Interaction Queues can be used.

Chatbot specific reports are planned to be added in 2019.

Assumptions

General Assumptions

  • Use Case Interdependencies include use cases not yet available in Genesys Engage cloud; however, they are planned for availability in 2019.
  • Use Case supports web & mobile chat, Facebook Messenger, Apple Business Chat, WhatsApp, and SMS.
  • This Use Case is supported by industry templates that contain examples of chatbot applications combining personalization, natural language understanding, AI, and microapps. Chatbot application requirements including required microapps will be confirmed during design. These application templates will be created for Financial Services, Telco, and Travel.
  • Handoff to agent is on the same channel.
  • Dialog Engine has been "trained" with intents.
  • Dialog Engine provides English and German language support for NLU capabilities.
  • Supported third-party NLU/bot platforms are Amazon Lex and Google Dialogflow.
  • Rich Messaging (for example, buttons, carousels, and list pickers) may require PS customization. SMS does not support Rich Messaging. Please review this pageand Designer documentation for what is currently available.
  • Integration to Knowledge Center is a customization task; an example integration code snippet can be provided.
  • Secure payment options vary by channel (for example, Apple Pay on Apple Business Chat is secure; SMS is not).
  • Designer user interface is used to configure chatbots and is currently available in U.S. English only.

Customer Assumptions

Interdependencies

All required, alternate, and optional use cases are listed here, as well as any exceptions.

All of the following required: At least one of the following required: Optional Exceptions
None

    Digital

        Digital

          None

          Premise Assumptions

          Cloud Assumptions

          • Customer selects one or more of the supported NLU platforms.
          • NLU configuration takes place in the native NLU interface (which may be embedded within Designer).

          Related Documentation

          Document Version