Skip to main content
ADK-101Axalon Original

Agentic Architecture & Design

Taught by Dan King, 4x Google Trainer of the Year

2 daysILTIntroductoryLoading...
Foundations2 DaysHands-On

Public class policy: Classes run with a minimum of 6 participants. If minimum enrollment isn't reached, you'll be notified 7 days before with options to transfer or receive a full refund.

Overview

Build production-ready AI agents from foundations to deployment. Master the cognitive loop, design patterns (Sequential, Router, Parallel), tool integration, and state management. Hands-on workshop approach with 20% theory, 60% labs, 20% building your own agent.

What You'll Learn

  • Build local agents with various architectures
  • Understand and apply the cognitive loop
  • Implement Sequential, Router, and Parallel agent patterns
  • Design effective tool integration strategies
  • Manage agent state and memory with Pydantic models
  • Calculate and optimize token economics

Who Should Attend

Developers new to agent development. Python basics and GCP account required.

Products Covered

ADKVertex AIGeminiCloud RunAgent Engine

Course Modules

1

Day 1: The Agentic Shift

Topics

  • Cognitive loop: Observation → Reasoning → Action → Reflection
  • Gemini 3 Thinking Mode and model-internal reasoning
  • ADK ecosystem overview
  • Agent Engine vs Cloud Run deployment models
  • First agent development

Learning Outcomes

  • Explain the cognitive loop and its components
  • Compare Agent Engine vs Cloud Run for different use cases
  • Build and run a basic ADK agent locally

Activities

Theory (45min)Lab: Building AI Agents FoundationLab: Build Your First AI CompanionWorkshop: Define agent use case
2

Day 2: Design Patterns & Tools

Topics

  • Sequential, Router, Parallel patterns
  • Tool types and integration strategies
  • Token economics and cost management
  • Budget protection and infinite loop prevention

Learning Outcomes

  • Select appropriate pattern for use case requirements
  • Integrate tools effectively with agents
  • Calculate and optimize token costs

Activities

Theory (45min)Lab: Multi-Tool AgentsLab: Empowering with ToolsLab: From Zero to AssistantWorkshop: Prototype pattern with cost estimate
3

Day 3: State & Memory

Topics

  • Context management strategies
  • Schema-based state with Pydantic models
  • Memory persistence patterns
  • Session management

Learning Outcomes

  • Design effective state schemas
  • Implement persistent memory for agents
  • Build a complete stateful agent

Activities

Theory (45min)Lab: ADK Crash Course (Sessions/Memory)Lab: Personalized Agents with Memory BankWorkshop: Implement stateful agent (2hr)

Get This Training

No public classes currently scheduled. Express interest below or request private training.

Request Private Session

Course Details

Course Code
ADK-101
Duration
2 days
Format
ILT
Level
Introductory
Price
Loading...

Questions About This Course?

Contact us for custom scheduling, group discounts, or curriculum customization.

Contact Us
Starting fromLoading...