Getting Started
Welcome
()
1. Introduction
Multi-agent systems: Core concepts
()
Introducing Agent Development Kit (ADK): Your AI building blocks
()
ADK quickstart: Building your first text-based agent
()
2. Diving Deeper into ADK Agents
Core agent types: LLM, workflow, and custom agents
()
LLM agents: The engine of intelligent conversation and reasoning
()
Building LLM agents: From basic prompts to tool-enabled power
()
Workflow agents: Orchestrating complex tasks with precision and order
()
Custom agents: Ultimate flexibility with Python logic
()
Strategic agent selection: Choosing the right ADK agent
()
3. Empowering Agents: Tools and Integrations
ADK's built-in toolbox: Essential capabilities for your agents
()
Function tools: Tailoring agent actions with Python
()
Expanding horizons: Integrating third-party tools and live data
()
Leveraging Google Cloud: Native ADK integrations and secure services
()
Tool design: Best practices for reliable and secure ADK agents
()
4. Orchestrating Multi-Agent Systems and Context
Hierarchical designs: Delegation, routing, and orchestration
()
Parallel agents: Concurrent execution for enhanced efficiency
()
Loop agents: Iterative processes and refinement
()
Conversational blueprint: Understanding session, state, and memory
()
Context-aware agents: Practical session and state management
()
Putting it all together: Advanced multi-agent orchestration with a coordinator
()
5. Advanced Agents: Persistent Artifacts and Lifecycle Callbacks
Artifacts: Giving agents lasting, versioned memory
()
Data artifacts: Best practices for naming, versioning, and namespaces
()
Callbacks: Customizing the agent lifecycle with precision hooks
()
6. Productionizing Agents: Deployment, Evaluation & Responsible AI
Deploying agents: Agent Engine, Cloud Run, and GKE
()
Operational excellence: Security, monitoring, and observability
()
Agent quality: Trajectory analysis and response evaluation
()
Responsible agents: Upholding safety, ethics, and trust
()
Conclusion
Course recap: The road ahead
()