Course Overview:

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.

After completing this course, participants will be able to:

  • Build an agent with tools using the Google Agent Development Kit.
  • Establish interaction patterns between multiple agents with parent-child relationships and flows.
  • Utilize features such as session memory, artifact storage, and callbacks.
  • Deploy a multi-agent app to Agent Engine.
  • Query an agent app running on Agent Engine

Upcoming Batches

Loading Dates...

Key Features:-

  • Practical, Hands-On Learning:

    • Emphasis on real-world application and practical implementation.
    • Extensive coding exercises and projects.
    • Focus on deploying functional multi-agent systems.

  • Comprehensive Tool Coverage:

    • In-depth training on the Agent Development Kit (ADK).
    • Detailed instruction on utilizing the Agent Engine.
    • Learning how to effectively integrate both tools.

  • Multi-Agent System Fundamentals:

    • Understanding core concepts of agent interaction and collaboration.
    • Designing agent architectures for various applications.
    • Learning about communication protocols and coordination mechanisms.

  • Deployment Strategies:

    • Techniques for deploying multi-agent systems in different environments.
    • Scalability and performance optimization.
    • Addressing real-world deployment challenges.

  • Real-World Applications:

    • Exploration of diverse applications of multi-agent systems.
    • Case studies and examples from various industries.
    • Focus on solving complex problems with agent-based solutions.

  • Agent Development Kit Specifics:

    • Learning the ADK’s API.
    • Developing custom agents.
    • Utilizing the ADK’s frameworks.

  • Agent Engine Specifics:

    • Agent Engine runtime enviroment.
    • Managing agent communications.
    • Agent Engine deployment options.

  • Collaborative Agent Design:

    • Methods for designing agents that effectively collaborate.
    • Strategies for conflict resolution and negotiation.
    • Techniques for building robust and resilient multi-agent systems.

  • Scalability and Robustness:

    • Methods of scaling multi-agent systems.
    • Error handling and fault tolerance.
    • Ensuring system stability.

Who Should Attend?

  • Machine learning engineers / Gen AI engineers.

What are the prerequisites for the training?

  • Python, Gen AI, Prompt Engineering, Gen AI tool use

    • Why Choose to Learn with CloudThat?

    • Specialized GCP Focus: CloudThat specializes in cloud technologies, offering focused and specialized training programs. We are Authorized Trainers for the Google Cloud Platform. This specialization ensures in-depth coverage of GCP services, use cases, best practices, and hands-on experience tailored specifically for GCP.
    • Industry-Recognized Trainers: CloudThat has a strong pool of industry-recognized trainers certified by GCP. These trainers bring real-world experience and practical insights into the training sessions, comprehensively understanding how GCP is applied in different industries and scenarios.
    • Hands-On Learning Approach: CloudThat emphasizes a hands-on learning approach. Learners can access practical labs, real-world projects, and case studies that simulate actual GCP environments. This approach allows learners to apply theoretical knowledge in practical scenarios, enhancing their understanding and skill set.
    • Customized Learning Paths: CloudThat understands that learners have different levels of expertise and varied learning objectives. We offer customized learning paths, catering to beginners, intermediate learners, and professionals seeking advanced GCP skills.
    • Interactive Learning Experience: CloudThat's training programs are designed to be interactive and engaging. We utilize various teaching methodologies like live sessions, group discussions, quizzes, and mentorship to keep learners engaged and motivated throughout the course.
    • Placement Assistance and Career Support: CloudThat often provides placement assistance and career support services. This includes resume building, interview preparation, and connecting learners with job opportunities through our network of industry partners and companies looking for GCP-certified professionals.
    • Continuous Learning and Updates: CloudThat ensures that our course content is regularly updated to reflect the latest trends, updates, and best practices within the GCP ecosystem. This commitment to keeping the content current enables learners to stay ahead in their GCP knowledge.
    • Positive Reviews and Testimonials: Reviews and testimonials from past learners can strongly indicate the quality of training provided. You can Check feedback and reviews about our GCP courses that can provide potential learners with insights into the effectiveness and value of the training.

    Learning objective of course:

    • Understand the fundamentals of multi-agent systems (MAS): Define key concepts, architectures, and applications of MAS.
    • Comprehend the role and capabilities of the Agent Development Kit (ADK): Learn its components, functionalities, and how it facilitates agent development.
    • Grasp the operation of the Agent Engine: Understand its runtime environment, deployment options, and management of agent interactions.
    • Learn about agent communication protocols: Understand standard protocols and develop custom communication strategies.
    • Understand different methods of agent coordination and collaboration: Learn how to design systems where agents can work together effectively.
    • Develop and implement intelligent agents using the ADK: Gain hands-on experience in building agents with specific behaviors and capabilities.

    Course Outline:- Download Course Outline

  • Explain how the Agent Development Kit compares to other tools such as the Google Gen AI SDK or LangChain.
  • Describe the parameters used to build an agent in the Agent Development Kit.

    • Basics of building an agent in the Agent Development Kit
    • 1 Lab

  • Discuss the importance of structured docstrings and typing when writing tool functions for agents.
  • Demonstrate the ability to provide tools to an agent.
  • List common and useful tools available for the Agent Development Kit agents, including LangChain tools

    • Enhance agents with tools and cover the growing breadth of available tools
    • 1 Lab

    • Manage communication and task-sharing between agents through parent-child relationships and flows to enable coordinated responses to queries.
    • 1 Lab

  • Describe the benefits of deploying agents, especially Multi-Agent Systems, to Agent Engine over self-hosting, such as in Vertex AI online predictions.
  • Demonstrate deploying to Agent Engine.
  • Demonstrate querying a deployed agent app.

    • Deploying agent apps to Agent Engine and querying response
    • 1 Lab

  • Evaluate agents within the Agent Development Kit.
  • Use the web interface to view evaluations

    • Evaluate agents within the Agent Development Kit
    • 1 Lab

  • Utilize sessions in an agent.
  • View and debug sessions in the Agent Framework web UI.
  • Utilize artifact storage

    • Provide agents session memory to iterate on a current state. Grant agents access to documents to enable them to craft and refine documents.
    • 1 Lab

    Select Course date

    Loading Dates...
    Add to Wishlist

    Course ID: 25216

    Course Price at

    Loading price info...
    Enroll Now

    The ADK is a toolkit designed to simplify the development of intelligent agents and multi-agent systems. It provides libraries, frameworks, and tools for building agents and managing their interactions.

    The Agent Engine is the runtime environment that executes and manages multi-agent systems. It handles agent communication, coordination, and deployment.

    The course will specify the programming languages that are used. Please check the course description. Python is often used in Agent based systems.

    Yes, the ADK and Agent Engine are designed for building and deploying real-world multi-agent systems in various domains.

    The course will cover deployment strategies, including how to configure and run the Agent Engine in different environments.

    The course will cover topics such as agent architecture, communication protocols, coordination mechanisms, deployment strategies, and practical applications of multi-agent systems.

    Yes, the course will emphasize practical, hands-on learning with coding exercises and real-world projects.

    After completing this course, you will be able to design, develop, and deploy your own multi-agent systems using the ADK and Agent Engine. You'll have the skills to build intelligent, collaborative applications.

    Yes, the course will address scalability, error handling, and fault tolerance to ensure your systems are robust and reliable.

    Yes, the course will cover standard and custom communication protocols for effective agent interaction.

    Enquire Now