🏆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
GCPCIADK

Build a Multi-Agent App Using Agent Development Kit (ADK) Training

In this course, you build a multi-agent sales proposal application to gather a company's public information, write and iteratively optimize a custom sales pitch, and then generate sales collateral.

Google Cloud
✓ Official training Google CloudLevel Intermediate⏱️ 0.5 day (4h)

What you will learn

  • Build and deploy a multi-agent process automation system using ADK
  • Implement sequential, loop, and parallel agent patterns
  • Develop automated research, drafting, and multi-collateral generation workflows
  • Deploy and test custom agents using the Agent Development Kit
  • Install and configure the Agent Development Kit (ADK) using the Agent Starter Pack.

Prerequisites

  • Working knowledge of Google Cloud
  • Knowledge of generative AI and multi-agent application basic concepts
  • Have competency in at least one language (such as Python, Java)
  • Be familiar with the basics of shell scripting, SQL

Target audience

  • Software engineers and application developers looking to build multi-agent systems for process automation and optimization.

Training Program

4 modules to master the fundamentals

Objectives
  • Describe the core capabilities and value of the Agent Development Kit (ADK)
  • Set up an ADK development environment using the Agent Starter Pack
  • Construct a SequentialAgent to coordinate multi-step sales proposal workflows
Topics covered
  • →Value and purpose of the Agent Development Kit (ADK)
  • →Installing ADK with the Agent Starter Pack
  • →Sequential agent design patterns for process management
Activities

Lab: Install ADK with the Agent Starter Pack

Lab: Build a SequentialAgent for Sales Proposal Management

Objectives
  • Explain the architectural pattern and state management of Loop Agents
  • Implement a LoopAgent to iteratively draft and refine personalized sales pitches
Topics covered
  • →Loop agent architectural patterns
  • →Managing state and context loops
  • →Iterative drafting and refinement of personalized pitches
Activities

Lab: Build a LoopAgent to refine personalized sales pitches

Objectives
  • Design asynchronous execution workflows using Parallel Agents
  • Configure a Parallel Agent to concurrently generate diverse sales collateral
Topics covered
  • →Parallel agent execution patterns
  • →Asynchronous agent workflows
  • →Generating diverse concurrent outputs (emails, slides, summaries)
Activities

Lab: Implement a Parallel Agent for concurrent collateral generation

Objectives
  • Configure the Agent Runtime environment for production deployment
  • Deploy and evaluate custom ADK agents against performance criteria
Topics covered
  • →Agent Runtime environment configuration
  • →Deploying custom ADK agents
  • →Testing and evaluation of agent performance
Activities

Lab: Deploy and test your complete Sales Proposal Engine

Related Trainings

Google Cloud

Build Agents with the Agent Development Kit

In this course, you'll learn to use the Agent Development Kit (ADK) to build systems where multiple AI agents collaborate on complex tasks. You'll start with the ADK agent model: how ADK represents agents, tools, and runners, and how a single agent is configured and run. You'll then make tools the model can call, persist session state across agents, and instrument the execution lifecycle with callbacks and plugins. Next, you'll orchestrate multiple agents using ADK's template workflow agents and graph-based workflows, and ground them in enterprise data through multi-source retrieval and MCP integrations. Finally, you'll deploy a multi-agent system to Agent Runtime as a managed service and register and share it through Gemini Enterprise so users across an organization can reach it.

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

Software engineers and application developers looking to build multi-agent systems for process automation and optimization.
A working knowledge of Google Cloud and basic knowledge of multi-agent systems.
You will recognize the value and purpose of the Agent Development Kit (ADK), install ADK with the Agent Starter Pack, create and configure LLM and workflow agents (sequential, loop and parallel), and deploy the application to Agent Runtime.
A sales proposal application. The tasks are: install ADK with the Agent Starter Pack, configure your root agent, create a sequential agent workflow, create a loop agent workflow, add a parallel agent workflow and deploy the application to Agent Runtime. A bonus task adds an executive summary one-pager.
The workshop lasts 4 hours and is led by a SFEIR Institute instructor. It is organized task by task: a demo, hands-on practice and a reflection for each step.
Yes. This is an official Google Cloud workshop delivered by SFEIR Institute, a certified Google Cloud Training Partner.

790€ excl. VAT

per learner

ReserveQuote