Google CCAI Training Overview
This Google Contact Center AI and Dialogflow training course teaches attendees how to design, develop, and deploy customer conversational solutions using Contact Center Artificial Intelligence (CCAI). Participants learn best practices for integrating conversational solutions with their existing contact center software, establishing a framework for human agent assistance, and implementing solutions securely and at scale.
Location and Pricing
This course is taught as a private, live online class for teams of 3 or more. All our courses are hands-on, instructor-led, and tailored to fit your group’s goals and needs. Most Accelebrate classes can be flexibly scheduled for your group, including delivery in half-day segments across a week or set of weeks. To receive a customized proposal and price quote for online corporate training, please contact us.
In addition, some courses are available as live, instructor-led training from one of our partners.
Objectives
All students will learn how to:
- Define what Google Contact Center AI is
- Explain how Dialogflow can be used in contact center applications
- Describe how natural language understanding (NLU) is used to enable Dialogflow conversations
- Implement a chat virtual agent
- Implement a voice virtual agent
- Describe options for storing parameters and fulfilling user requests
- Deploy a virtual agent to production
- Identify best practices for design and deployment of virtual agents
- Identify key aspects, such as security and compliance in the context of contact centers
Prerequisites
All students must have taken Accelebrate's Google Cloud Fundamentals: Core Infrastructure course or have equivalent experience. Knowledge of a programming language such as Python or JavaScript is desired, but not required.
Outline
Expand All | Collapse All
Overview of Contact Center AI
- Define what Contact Center AI (CCAI) is and what it can do for contact centers
- Components of the CCAI Architecture: Speech Recognition, Dialogflow, Speech Synthesis, Agent Assist, and Insights
- The role each component plays in a CCAI solution
- Quiz - Contact Center AI fundamentals
Conversational Experiences
- The basic principles of a conversational experience
- The role of conversation virtual agents in a conversation experience
- How STT (speech to text) can determine the quality of a conversation experience
- Demonstrate and test how speech adaptation can improve the speech recognition accuracy of the agent
- The different NLU (natural language understanding) and NLP (natural language processing) techniques and the role they play in conversation experiences
- The different elements of a conversation (intents, entities, etc.)
- Use sentiment analysis to help with the achievement of a higher-quality conversation experience
- Improve conversation experiences by choosing different TTS voices (Wavenet vs. Standard)
- Modify the speed and pitch of a synthesized voice
- Leveraging the SSML to modify the tone and emphasis of a synthesized passage
- Quiz - Conversational Experiences
Fundamentals of Building Conversations with Dialogflow
- User roles and their journeys
- Write personas for virtual agents and users
- Model user-agent interactions
- The basic elements of the Dialogflow user interface
- Building a virtual agent to handle identified user journeys
- Training the NLU model through the Dialogflow console
- Define and test intents for a basic agent
- Training the agent to handle expected and unexpected user scenarios
- The different types of entities and when to use them
- Entities
- Define and test entities on a basic agent
- Implement slot filling using the Dialogflow UI
- When Mega Agent might be used
- Adding access to a knowledge base for your virtual agent to answer customer questions straight from a company FAQ
- Quiz - DF Fundamentals: Intents and Entities
- Lab - DF Fundamentals: Build a Basic Virtual Chat Agent That Uses Intents and Entities
- Lab - Creating a Knowledge Base Connector
Maintaining Context in a Conversation
- Follow-up intents
- The scenarios in which context should be used
- The possible statuses of a context (active versus inactive context)
- Dialogs using input and output contexts
- Quiz - Context
- Lab - Context: Add to your virtual chat agent using input and output contexts to map more intricate conversational scenarios
Moving from Chat agent to Voice agent
- Two ways that the media type changes the conversation
- Configuring the telephony gateway for testing
- Testing a basic voice agent
- Modifing the voice of the agent
- Different media types can have different responses
- Modifications needed when moving to production
- Telephony integration for voice in a production environment
- Quiz - Chat versus Voice agent.
- Lab - Voice Agent: Add voice to your virtual agent.
Taking Actions with Fulfillment
- The role of fulfillment with respect to Contact Center AI
- What needs to be collected in order to fulfill a request
- Existing backend systems on the customer infrastructure
- Firestore to store mappings returned from functions
- Interaction with customers’ data storage will vary based on their data warehouses
- Fulfillment using Cloud Functions
- Fulfillment using Python on AppEngine
- Apigee for application deployment
- Quiz - Fulfillment
- Lab - Fulfillment: Using cloud functions to persist and query data from a database
Testing and Logging
- Debug a virtual agent by testing intent accuracy
- Debug fulfillment by testing the different functions and integrations with backend systems through API calls
- Implementing version control to achieve more scalable collaboration
- Log conversations using Cloud Logging
- Ways that audits can be performed
- Quiz - Testing and Logging
- Lab - Logging: Use Cloud Logging to debug your virtual agent code
Intelligent Assistance for Live Agents
- Recognize use cases where Agent Assist adds value
- Identify, collect, and curate documents for knowledge base construction
- Set up knowledge bases
- FAQ Assist
- Document Assist
- The Agent Assist UI
- Dialogflow Assist
- Smart Reply
- Real-time entity extraction
- Quiz - Helping agents enhance the customer experience with knowledge bases, smart replies, and document assistance
Drawing Insights from Recordings
- Audio recordings using the Speech Analytics Framework (SAF)
- Lab: Use the Speech Analytics Framework to draw insights from contact center logs
Integrating a Virtual Agent with Third Parties
- Using Dialogflow API to programmatically create and modify the virtual agent
- Connectivity protocols: gRPC, REST, SIP endpoints, and phone numbers over PSTN
- Replacing existing head intent detection on IVRs with Dialogflow intents
- Virtual agent integration with Google Assistant
- Virtual agent integration with messaging platforms
- Virtual agent integration with CRM platforms (such as Salesforce and Zendesk)
- Virtual agent integration with enterprise communication platforms (such as Genesys, Avaya, Cisco, and Twilio)
- The ability that telephony providers have of identifying the caller and how that can modify the agent design
- Incorporating IVR features in the virtual agent
- Quiz - IVR Features
- Quiz - Common platforms of integration
- Quiz - Contact Center AI integration points
Environment Management
- Creating Draft and Published versions of your virtual agent
- Creating environments where your virtual agent will be published.
- Loading a saved version of your virtual agent to Draft.
- Changing which version is loaded to an environment.
- Quiz - Environment Management
- Lab - Use the Dialogflow Environment Management feature to deploy a draft version of your virtual agent to a new environment
Methods of Compliance with Federal Regulations
- Describe two ways that security can be implemented on a Contact Center AI integration
- Identify current compliance measures and scenarios where compliance is needed
- Quiz – Audit
Best Practices for Virtual Agents
- Converting pattern matching and decision trees to smart conversational design
- Situations that require escalation to a human agent
- Support multiple platforms, devices, languages, and dialects
- Dialogflow's built-in analytics to assess the health of the virtual agent
- Agent validation through the Dialogflow UI
- Monitor conversations and Agent Assist
- DevOps and version control framework for agent development and maintenance
- Consider enabling spell correction to increase the virtual agent's accuracy
- Quiz - Best practices
Google Implementation Methodology (Partners only)
- The stages of the Google Implementation Methodology
- The key activities of each implementation stage
- Google's support assets for Partners
Conclusion
Training Materials
All GCP training students receive comprehensive courseware.
Software Requirements
Students must have a modern web browser (ideally Chrome) and Internet access.
