🏆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
GCP300CXAGENTSTUDIO

Build Agents with CX Agent Studio Training

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.

Google Cloud
✓ Official training Google CloudLevel Advanced⏱️ 2 days (14h)

What you will learn

  • Design multi-agent architectures and developer-first workflows.
  • Evaluate CX agent performance.
  • Implement deterministic logic.
  • Create and maintain data stores that enhance CX agents.
  • Deploy a CX agent to various digital channels.
  • Leverage CX agent tools and connectors to integrate with various providers.
  • Escalate to human agents.
  • Apply industry best practices for a successful launch.
  • Utilize Native Audio to configure natural voice-based interactions.

Prerequisites

  • Basic understanding of Google Cloud and LLMs.

Target audience

  • Conversational Architects, Conversational Designers, Data Engineers/Scientists and other roles supporting implementation of AI agents

Training Program

7 modules to master the fundamentals

Objectives
  • Refresh your knowledge about AI agents on Google Cloud and CX Agent Studio.
  • Create production-ready agents in CX Agent Studio.
Topics covered
  • →Then and now
  • →AI agents and conversational AI solutions
  • →Gemini Enterprise for Customer Experience (CX)
  • →CX Agent Studio overview
Activities

Lab: Create CX agents ready for production

Objectives
  • Design multi-agent architectures to manage complexity.
  • Apply best practices for instructions.
  • Implement deterministic logic.
  • Configure enterprise-ready features.
Topics covered
  • →Product demonstration
  • →Build and refine multi-agent architecture
  • →Hybrid versus deterministic agents
  • →Make your CX agents enterprise ready
Activities

Lab: Use CX Agent Studio memory and deterministic capabilities

Objectives
  • Build agents programmatically.
  • Configure and troubleshoot Native Audio voice agents.
Topics covered
  • →Programmatic access to CX Agent Studio
  • →Evolution of audio in AI Agents
Activities

Lab: Configure and troubleshoot voice-based agents in CX Agent Studio

Objectives
  • Differentiate between data store types
  • Create a data store
  • Leverage data stores and connectors
Topics covered
  • →Introduction to Agent Search and data store agents
  • →Core capabilities and technical advantages of data store agents
  • →Use cases for data store agents
  • →Phases of data store agent implementation
  • →Create a data store in CX Agent Studio
  • →Connection and configuration
  • →Common search configurations
  • →Common issues and troubleshooting
Activities

Lab: Leverage data store and connectors in your CX Agent Studio

Objectives
  • Align agent responses with defined company rules.
  • Configure guardrails to protect your CX agent.
  • Set up Memory for a CX agent.
  • Implement custom webhooks.
Topics covered
  • →Foundations and methods of CX Agent evaluation
  • →Test case development and metrics
  • →Advanced tuning and runs
Activities

Lab: Evaluate CX Agent Studio and implement the Quality Hill Climbing process

Lab: Use CX Agent Studio memory and deterministic capabilities

Objectives
  • Deploy the CX agent to various digital channels.
  • Escalate to human agents using Google Cloud CCaaS and Gemini Enterprise for Customer Experience.
  • Integrate with third party telephony services.
Topics covered
  • →Integrate CX agents with first- and third-party providers
  • →Digital channel integrations
  • →Third-party telephony integration
  • →Human escalation to third-party services
  • →Human escalation to Gemini Enterprise for CX
  • →Integration with Agent Assist
  • →Gemini Enterprise for CX integration through the API
Activities

Lab: Deploy agents to the web and third party channels from CX Agent Studio

Objectives
  • Outline the industry best practices for a successful launch.
  • Recall available compliance languages.
Topics covered
  • →Strategic alignment and planning
  • →Success metrics and visibility
  • →Launch execution and technical readiness
  • →Trust, safety and global readiness

Related Trainings

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.
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

Conversational architects and conversational designers, data engineers and data scientists, and any technical role involved in implementing AI agents for customer experience.
A basic understanding of Google Cloud and of large language models (LLMs). No prior experience with CX Agent Studio is required.
End-to-end CX agents with instructions, tools and sub-agents that work for both text and voice, extended with Agent Search data stores, deployed to web, API, telephony and CCaaS channels, with evaluation, monitoring and logging in place.
Yes. A module is dedicated to programmatic management and voice agents, including Native Audio for natural voice interactions, with a lab on configuring and troubleshooting voice agents in CX Agent Studio.
Labs cover building production-ready CX agents, memory and deterministic capabilities, voice agents, data stores and connectors, agent evaluation with the Quality Hill Climbing process, and deploying agents to web and third-party channels.
The training lasts 2 days (14 hours) and alternates theory, product demonstrations and hands-on labs. It closes with the essentials of a successful launch: strategic alignment, success metrics, technical readiness, trust and safety.
This course is contracted via Google Cloud only: it cannot be purchased directly from SFEIR Institute. Contact us to learn how to order it through Google Cloud.
Our training organizations SFEIR SAS and SFEIR-Est are Qualiopi certified for training activities. Contact us for a quote.

Request a quote

ReserveQuote