Building Agents with Google ADK 2.0
Google ADK 2.0
Build agents, tools and multi-step workflows with Google ADK 2.0, then evaluate them.
What is Google ADK?
Google ADK (Agent Development Kit) is a framework for building AI agents. In this course, you use its Python library to connect a model to instructions and tools, run conversations and compose multi-step workflows. ADK runs the agent’s conversation loop and handles its events; your application still chooses the available tools and checks their results.
Build a documentation assistant that answers a rollback question from a bundled guide. Start with its model and instructions, then add a read tool and inspect the tool calls and returned answer. Later lessons use the documentation scenario to explain workflows, human approval and evaluation. Each download contains its own implementation and record.
What you'll learn
- Define an ADK agent with function tools, run it from Python with a Runner and session service, and read its event stream.
- Connect an agent to MCP servers with McpToolset, validate typed function arguments and require confirmation for writes.
- Persist sessions in SQLite and search conversation memory while the process runs; guard model and tool calls with callbacks and plugins.
- Build graph workflows with conditional edges, pause one for human approval with RequestInput and delegate to sub-agents.
- Score an agent's tool trajectory and final response with AgentEvaluator before you change it.
Lessons
Module 1 · 6 lessons · about 2 hoursAgents and tools
Define an agent, run its conversation and add tools, saved state and execution guards.
Build your first ADK agent with GeminiRead
Build a documentation assistant with Google ADK, understand its model and instructions, and run it from the terminal or development Web UI.
Run an agent and read its event streamRead
Use Python Runner to manage an ADK conversation, inspect model and tool events, select the final answer and handle streaming and model-call limits.
Give an agent typed function toolsRead
Give a Google ADK 2.0 agent typed function tools, validate every call with Pydantic before it runs, and require human approval for the tool that writes.
Connect an agent to MCP servers with McpToolsetRead
Attach a typed MCP server to a Google ADK 2.0 agent with McpToolset, expose only the tools it needs, read what reaches the model and catch a failed start.
Persist sessions and search conversation memoryRead
Persist Google ADK 2.0 sessions in SQLite with DatabaseSessionService, keep user state across restarts and recall earlier conversations with load_memory.
Guard model and tool calls with callbacks and pluginsRead
Redact matching access-key identifiers before storage or model use, and reject file-tool reads outside the workspace with ADK callbacks and plugins.
Module 2 · 6 lessons · about 2 hoursWorkflows and evaluations
Connect steps with graph routes or Python, add approval and delegation, then evaluate tool use and answers.
Build a graph workflow from nodes and edgesRead
Build a release-notes workflow with function nodes, a typed agent node and a deterministic check that every commit reaches the output.
Route a workflow with conditional edgesRead
Route documentation build logs with Python, use a default edge for incomplete runs and ask an agent for link suggestions only when needed.
Pause a workflow for human approvalRead
Pause a migration workflow with the SQL attached, validate a reviewer decision and resume the same session to apply or reject the change.
Build dynamic workflows in PythonRead
Review changed documentation pages with dynamic child nodes, deterministic lint checks and a bounded agent fix loop with retries and timeouts.
Delegate to sub-agents through a coordinatorRead
Build a documentation review team with a coordinator, two typed specialists and an event check that both delegations ran.
Evaluate an agent's tool trajectory and responseRead
Write evaluation cases for tool use and complete answers, run ADK AgentEvaluator and understand the limits of trajectory, ROUGE and judge scores.
Module 3 · 5 lessons · about 2 hoursWorkflow patterns
Choose a workflow structure for drafting, revision, independent branches and nested delegation.
Choose an ADK workflow patternRead
Compare ADK workflow patterns by dependencies, control and failure policy, then inspect the real lesson graphs without calling a model.
Generate and review a release announcementRead
Build an ADK writer and reviewer that compare a release announcement with changelog facts, then enforce the typed verdict in code.
Revise a changelog line with a bounded loopRead
Refine a changelog line in an ADK 2.0 graph loop: a lint checks each draft, a back-edge sends problems to a reviser, and a state counter stops the loop.
Run independent workflow branches and gather resultsRead
Run ADK 2.0 workflow branches in parallel and merge them with a JoinNode, then see one failed branch fail the graph and a dynamic parent keep the rest.
Delegate an upgrade guide through a bounded agent treeRead
Build a depth-limited ADK AgentTool tree for an upgrade guide, check its source paths and share a model-call budget across nested runs.
