A free course for software engineers on AI agents. Learn the fundamentals, build with real tools, and ship to production.
The big picture - what agents are, why they matter, and when to use them.
LLMs as the reasoning engine - how models plan, decide, and generate.
Function calling, tool design, and connecting agents to the real world.
ReAct, reflection, planning, and other core patterns.
How agents remember things - sessions, context windows, and long-term memory.
How agents break down complex tasks and make decisions.
When one agent isn't enough - coordination, delegation, and teamwork.
Going beyond basic retrieval - agents that search, evaluate, and refine.
How to know if your agent actually works - metrics, evals, and observability.
Keeping agents trustworthy - security, alignment, and responsible AI.
The journey from demo to deployed - CI/CD, rollout, and operations.
The Google Cloud AI stack for agents - what's available and how it fits together.
Hands-on - build a working agent with ADK step by step.
How agents talk to tools and to each other using open standards.
Giving AI coding agents context about your project with a standard config file.
How MCP works under the hood, MCP vs. CLI tools, and security considerations.
Packaging reusable domain expertise as portable skill modules.
Managing agent control flow - patterns, frameworks, and best practices.
Resources, codelabs, community, and next steps.