Google's Free 5-Day AI Agents Course (For Builders Who Code in Python)
Hands-on Python course with deep-dive whitepapers
Google’s ML researchers just released a hands-on course for building production-ready AI agents. It’s free, self-paced, and uses Python with their Agent Development Kit (ADK).
Even if you don’t program in Python, the five whitepapers below alone are worth reading to deepen your understanding of agent architecture, tools, memory, evaluation, and production deployment.
What’s Included
The 5-Day AI Agents Intensive originally ran as a live program in November 2025. Now it’s available as a self-paced Kaggle Learn guide.
Here’s what you’re actually building across the five days:
1 - Introduction to Agents: Build your first AI agent using Google’s Agent Development Kit (ADK) and Gemini. Then build your first multi-agent system. You’ll see how agentic architectures differ from traditional LLM applications.
2 - Agent Tools & MCP: Create custom tools by turning your Python functions into agent actions. Implement the Model Context Protocol (MCP) and learn how agents pause for human approval before continuing operations.
3 - Context Engineering: Make agents stateful. Manage conversation history, implement working memory within sessions, and give agents long-term memory that persists across conversations.
4 - Agent Quality: This is where most prototypes fail. Learn observability through logs, traces, and metrics. Evaluate your agents using LLM-as-a-Judge and Human-in-the-Loop methods.
5 - Prototype to Production: Deploy your agent to Vertex AI Agent Engine on Google Cloud. Build multi-agent systems using the Agent2Agent (A2A) Protocol.
Who This Is For (And Who It Isn’t)
This course is for builders who code in Python.
You need a Kaggle account (phone-verified), a Google AI Studio account with API key access, and a willingness to write Python. Each day combines whitepapers, hands-on codelabs, and optional livestream recordings.
Getting Started
The full course materials are here: 5-Day AI Agents Intensive Course
Each day includes:
A whitepaper covering the conceptual foundations
A podcast episode summarizing the material
Hands-on codelabs in Kaggle notebooks
Optional recorded livestreams with Google researchers
The entire course is self-paced.
Stay curious. Stay hands-on.
-James
This article comes at the perfect time, making the distinction between traditional LLM applications and agentic acrhitectures so incredibly clear and building on the insightful discussions you always bring to the forefront of AI development.
Nice post James. Read the first whitepaper already. I wonder if Truist could use an agentic system for the workflows I am engineering.