LEARN WITH A CLEAR DIRECTION
Learn ADK agents on the JVM: instructions, tools, sessions, events, orchestration and deterministic evaluation.
Learn ADK agents on the JVM: instructions, tools, sessions, events, orchestration and deterministic evaluation. Follow six teaching modules, each with a practical assignment, then combine the skills in the final project. Start with the introduction even if the tools are familiar: it defines the scope and boundaries of the path.
Self-paced. Complete each exercise and use its checkpoint before moving to the next module. Revisit any prerequisite you cannot yet demonstrate.
THE CURRICULUM
13 lessons across 7 modules. Open a module to explore its lessons and practical work.
Separate an agent framework from the model and its deployment.
Ready to move on when: You can justify the agent loop rather than adding one by default.
Create a small runnable JVM program before adding tools.
Ready to move on when: You can trace one input through the runner to its final response.
Use typed boundaries for application capabilities.
Ready to move on when: Tool safety is enforced even if the model ignores its instructions.
Control what each run remembers.
Ready to move on when: You can clear or replace session memory without losing authoritative business data.
Compose agents only where the separation helps.
Ready to move on when: You can show a measurable reason for each additional agent.
Test decisions and failure paths independently of model variability.
Ready to move on when: Your report separates model decision errors from tool implementation errors.
Build a support triage agent with read-only tools, bounded execution and a reproducible evaluation suite.
Ready to move on when: Demonstrate every acceptance criterion and explain the tradeoffs without relying on the lesson text.
PROVE YOUR SKILLS
Use the final review rubric to identify gaps. Lesson completion tracks study progress; readiness comes from independently demonstrating the work.
Open the portfolio review rubric →