Develop Conversational Agents on Google Cloud
Conversational Agents, part of AI Applications, is an intelligent, conversational (GUI) interface. It uses an AI development system with access to SDKs and APIs in multiple languages. In this course, you will learn how to leverage Conversational Agents to design and build conversational agents on Google Cloud.
- Duration: 3 days
- Languages: English, German
- Level: Introductory
- Group size: Up to 16
What you'll learn
- Understand the different kinds of conversations available with an artificial intelligent (AI) agent.
- Design an AI agent for a deterministic intent-based domain.
- Understand how a user's request is translated into an action and response.
- Use webhooks to access data and products that are not part of the agent.
- Handle user errors and unexpected requests.
- Use the graphical user interface (GUI) to develop an agent.
- Gain a working knowledge of the testing tools available in the GUI.
- Integrate a chatbot into external user interfaces.
- Incorporate generative AI features into your agent.
Prerequisites
- Some familiarity with a graphical user interface for Conversational Agents will ease the learning process.
- Understanding JSON is helpful.
Course outline
Introduction to Conversational Agents
- Google's goals for virtual agents
- Virtual agent product suites
Introduction to conversational design
- Convergent and divergent approaches
- Conversation design strategy
Steering bot design basics
- Use cases
- Virtual agents
- Start pages
- Routes
- Pages
Implementing bot design
- Use case review
- Agent architecture
- Creating the virtual agent
- Creating the route
- Testing the route
Entities
- Introduction to entities
- System entity types
- Custom entity types
- Managing entities in an agent
Parameters
- Introduction to parameters
- Parameters from intents
- Preset parameters
- Parameters from webhooks
Event handlers
- Definition of event handlers
- Page, flow event handler, and scope rules
- Form event handler and scope rules
Versions and environments
- Version management in Conversational Agents
- Environment management in Conversational Agents
Testing
- Validation
- Publication
- Simulation
Fulfillment
- Introduction to fulfillment
- Examples of static fulfillment
Integrations
- Google Messenger
- Conversational Phone Gateway
Webhooks
- Why have a webhook?
- Types of webhooks
- Setting up a fulfillment webhook
- Modifications for a JSON response webhook
Route groups
- Introduction to route groups
- Managing a route group
Design techniques
- The concept of a flow
- Steering bot designs
- The concept of guardrails
- Design principle
Generators and generative fallback
- Overview of generators
- Overview of generative fallback
Related courses
Gemini Enterprise Essentials for Business and Power Users
This course equips business professionals with essential skills for leveraging Gemini Enterprise. It covers generative AI basics, effective prompting, and using Gemini Enterprise for enterprise-wide search and assistance. The training also details NotebookLM's features for gaining deep insights into proprietary documents and explains different AI agent types, including the Deep Research Agent and no-code agents created with Agent Designer.
Generative AI Leader
In this course, you will take a journey from a broad overview of gen AI to understanding how to leverage gen AI and Google Cloud for organizational transformation.
Introduction to AI and Machine Learning on Google Cloud
This course introduces Google Cloud's AI and machine learning (ML) capabilities, with a focus on developing both generative and predictive AI projects. It explores the various technologies, products, and tools available throughout the data-to-AI lifecycle, empowering data scientists, AI developers, and ML engineers to enhance their expertise through interactive exercises.
Not sure which course fits?
Book a 30-minute call. We'll look at where your team is, what they need to be able to do, and put together either a specific course date or a tailored learning plan.