Diagram of a user request entering an application boundary, passing through an ADK runner and workflow to an LLM agent, with events written to a session service and deterministic controls surrounding external actions.
Free preview You are viewing part of Google ADK Agents Workshop for free. Unlock the full course for $247
Diagram of a user request entering an application boundary, passing through an ADK runner and workflow to an LLM agent, with events written to a session service and deterministic controls surrounding external actions.
A bounded ADK application separates probabilistic agent behavior from execution infrastructure, session data, and application-owned controls.

Establish an accurate, version-pinned ADK mental model and implement the smallest useful agent before introducing tools or multi-agent complexity.

Module objectives

  • Verify the workshop SDK version, supported languages, reference implementation, and language-specific assumptions against current official documentation and release notes.
  • Explain the responsibilities of agents, models, instructions, runners, workflows, events, sessions, state services, and deterministic application code.
  • Implement and run a small bounded agent with inspectable events and explicit session identifiers.
  • Decide when a direct model call, deterministic function, single ADK agent, or larger agent system is warranted.

Detailed topic content is generated and researched separately so each topic maintains its own source trail.

Recap slides

This module in 6 slides

Click through for a quick overview, or use your arrow keys.

Go deeper

Put this module to work

Suggested time: 3 to 4 hours

Real-world scenario

A developer builds their first Google ADK agent and gives it a long instruction covering everything: tone, policy, pricing and what to do with refunds. It works in the web UI, then makes inconsistent decisions in production. This module sets the foundation: how ADK runs an agent, how to write instructions with clear boundaries, and which decisions belong in deterministic code instead of the model.

Step-by-step walkthrough

  1. Set up the current ADK version in a fresh environment, following the official quickstart.
  2. Create a minimal agent with a model, name, description and instruction, and run it with the dev UI and the CLI.
  3. Trace one run: how the runner, session and events fit together.
  4. Rewrite the instruction into labeled sections: role, scope, rules, escalation and output.
  5. List the decisions in your use case that should be code, not model judgment.

Common mistakes and how to fix them

MistakePutting policy logic in the instruction.
FixRules that must never be broken belong in code or tools.
MistakeSkipping the event log.
FixRead the events for each run. They show exactly what happened.
MistakeCopying old examples.
FixADK evolves quickly. Check that examples match your installed version.
Daniel Morris

Field note from Daniel

I always start a new platform by watching exactly what it does on one simple request, step by step. With ADK, that means reading the events. Once you understand one run end to end, everything you build on top is easier to debug.

Try this

Give your agent an instruction that conflicts with a tool’s behavior. Watch the events to see which one wins, and fix the conflict.

Before you move on

Your checklist is saved in this browser.

Interactive tool

Agent opportunity scorer

Rate your idea on five factors and get a recommendation: agent, plain workflow, or simplify first. Your work is saved in this browser.

Interactive tool

Autonomy envelope builder

List the actions your agent might take and sort each into Do alone, Ask first or Never. Your work is saved in this browser.

Like what you see? The full course goes much deeper.All modules, topics, interactive tools, knowledge checks and your certificate. Backed by a 30-day money-back guarantee.

Enroll now for $247