🏆SFEIR is the Google Cloud EMEA Training Partner of the Year 2025🤝New partnership: Official GitLab Training🤖New training: AI-Augmented Developer
🏆SFEIR is the Google Cloud EMEA Training Partner of the Year 2025🤝New partnership: Official GitLab Training🤖New training: AI-Augmented Developer
GCP200CONVAI

Develop Conversational Agents on Google Cloud Training

Conversational Agents, part of AI Applications, is an intelligent, conversational (GUI) interface. Conversational Agents 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.

Google Cloud
✓ Official training Google CloudLevel Intermediate⏱️ 3 days (21h)

What you will 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.

Target audience

  • Conversational designers, developers, and business analysts

Training Program

15 modules to master the fundamentals

Objectives
  • Describe the goals of virtual agent development and product suites.
Topics covered
  • →Google's goals for virtual agents
  • →Virtual agent product suites
Activities

Lab: Exploring the Conversational Agents User Interface

Objectives
  • Understand virtual agent design
Topics covered
  • →Convergent and divergent approaches
  • →Conversation design strategy
Objectives
  • Design a basic steering bot using Conversational Agents
Topics covered
  • →Use cases
  • →Virtual agents
  • →Start pages
  • →Routes
  • →Pages
Objectives
  • Create an agent, a route, intents, and pages.
  • Implement routes without parameters.
  • Use test agent for testing.
Topics covered
  • →Use case review
  • →Agent architecture
  • →Creating the virtual agent
  • →Creating the route
  • →Testing the route
Activities

Lab: Conversational Agents: Bot Building Basics

Objectives
  • Access entity parameters.
  • Create custom regular expression (RegEx) entities.
  • Create custom list entities.
  • Use current recommended practices for extending a system entity class.
Topics covered
  • →Introduction to entities
  • →System entity types
  • →Custom entity types
  • →Managing entities in an agent
Objectives
  • Manipulate parameters using various methods.
Topics covered
  • →Introduction to parameters
  • →Parameters from intents
  • →Preset parameters
  • →Parameters from webhooks
Activities

Lab: Conversational Agents: Parameter Manipulation

Objectives
  • Understand event handlers and how they are used in Conversational Agents.
Topics covered
  • →Definition of event handlers
  • →Page, flow event handler, and scope rules
  • →Form event handler and scope rules
Objectives
  • Use version testing.
  • Use environments for different audiences.
Topics covered
  • →Version management in Conversational Agents
  • →Environment management in Conversational Agents
Activities

Lab: Conversational Agents: Managing Environments

Objectives
  • Validate for static analysis.
  • Publish to pretest user acceptance testing (UAT).
  • Simulate for unit testing.
Topics covered
  • →Validation
  • →Publication
  • →Simulation
Activities

Lab: Debugging the Agent Using Test Agent

Objectives
  • Use text, conditional, and custom fulfillment.
Topics covered
  • →Introduction to fulfillment
  • →Examples of static fulfillment
Objectives
  • Configure Google Messenger and Conversational Phone Gateway.
Topics covered
  • →Google Messenger
  • →Conversational Phone Gateway
Objectives
  • Recognize the different types of webhooks.
  • Set up a webhook with fulfillment response.
  • Set up a webhook JSON response.
Topics covered
  • →Why have a webhook?
  • →Types of webhooks
  • →Setting up a fulfillment webhook
  • →Modifications for a JSON response webhook
Objectives
  • Set up a flow route group.
  • Set up a session route group.
Topics covered
  • →Introduction to route groups
  • →Managing a route group
Activities

Lab: Configuring a Route Group for Your Virtual Agent

Objectives
  • Use flows to speed the development of an agent.
  • Use guardrails to prevent problems in agent design.
Topics covered
  • →The concept of a flow
  • →Steering bot designs
  • →The concept of guardrails
  • →Design principle
Objectives
  • Use generators and generative fallback in virtual agents.
Topics covered
  • →Overview of generators
  • →Overview of generative fallback
Activities

Lab: Conversational Agents with Generative Fallbacks

Related Trainings

Google Cloud

Build Agents with CX Agent Studio

In this course you will learn how to create, deploy and integrate agents in CX Agent Studio. You will create agents end-to-end including instructions, tools and sub-agents that work both for text and voice. Additionally, you will learn the different ways you can deploy the agent as well as integrations via web, API, telephony and CCaaS solutions. Finally, you will implement evaluations and configure monitoring and logging to understand the performance of your agent. Contracting via Google Cloud only.

2 d
Advanced
Google Cloud

Build Production-Ready Agents on Google Cloud

In this course, you will use your knowledge of developing agents using Agent Development Kit to productionize agents using Google's Agentic Stack on Google Cloud. After reviewing the agentic stack and different deployment targets, you will build an agent using session, memory and example services available within Google Cloud. You will integrate external tools using Model Context Protocol (MCP) and communicate with other agents using Agent2Agent (A2A) protocol. Finally, you will design applications with human-agent interaction in mind.

1 d
Advanced
Google Cloud

Deploy multi-agent systems with Agent Development Kit and Agent Engine

In this course, you'll learn to use the Google Agent Development Kit to build complex, multi-agent systems. You will build agents equipped with tools, and connect them with parent-child relationships and flows to define how they interact. You'll run your agents locally and deploy them to Vertex AI Agent Engine to run as a managed agentic flow, with infrastructure decisions and resource scaling handled by Agent Engine.

1 d
Advanced
View all trainings →

Upcoming sessions

No date suits you?

We regularly organize new sessions. Contact us to find out about upcoming dates or to schedule a session at a date of your choice.

Register for a custom date

Quality Process

SFEIR Institute's commitment: an excellence approach to ensure the quality and success of all our training programs. Learn more about our quality approach

Teaching Methods Used
  • Lectures / Theoretical Slides — Presentation of concepts using visual aids (PowerPoint, PDF).
  • Technical Demonstration (Demos) — The instructor performs a task or procedure while students observe.
  • Guided Labs — Guided practical exercises on software, hardware, or technical environments.
  • Quiz / MCQ — Quick knowledge check (paper-based or digital via tools like Kahoot/Klaxoon).
Evaluation and Monitoring System

The achievement of training objectives is evaluated at multiple levels to ensure quality:

  • Continuous Knowledge Assessment : Verification of knowledge throughout the training via participatory methods (quizzes, practical exercises, case studies) under instructor supervision.
  • Progress Measurement : Comparative self-assessment system including an initial diagnostic to determine the starting level, followed by a final evaluation to validate skills development.
  • Quality Evaluation : End-of-session satisfaction questionnaire to measure the relevance and effectiveness of the training as perceived by participants.

Frequently Asked Questions

Developers and conversational designers who want to build AI-powered conversational agents on Google Cloud, as well as technical teams delivering chatbot and virtual-assistant experiences.
Basic familiarity with Google Cloud and with APIs is recommended. Some programming experience helps for the webhook and fulfillment parts, but is not strictly required.
You will be able to design deterministic intent-based agents, manage entities and parameters, handle events, connect external data through webhooks, and add generative fallback for more natural conversations.
Yes. Beyond classic intent-based design, the training covers generators and generative fallback so your agents can respond naturally when no predefined intent matches.
The training lasts 3 days and alternates theory, live demonstrations and hands-on labs on real Google Cloud projects.
Our training organizations SFEIR SAS and SFEIR-Est are Qualiopi certified for training activities. Contact us for a quote.

2,370€ excl. VAT

per learner

ReserveQuote