What is the 5-Day AI Agents Intensive?
https://rsvp.withgoogle.com/events/google-ai-agents-intensive_2025/home
This 5-day online course was crafted by Google’s ML researchers and engineers to help developers explore the foundations and practical applications of AI agents. You’ll learn the core components – models, tools, orchestration, memory and evaluation. Finally, you’ll discover how agents move beyond LLM prototypes to become production-ready systems.
Each day blends conceptual deep dives with hands-on examples, codelabs, and live discussions. By the end, you’ll be ready to build, evaluate, and deploy agents that solve real-world problems.
How does the intensive work?
https://rsvp.withgoogle.com/events/google-ai-agents-intensive_2025/home
Everyday, participants will receive the following:
- 📚 Daily Assignments
This includes the whitepapers, a companion podcast (generated by NotebookLM) and companion codelabs that you can complete at your own pace. - 💬 Discord Discussion Threads
Kaggle’s Discord server will have a dedicated channel for focused discussion on the reading. It's an excellent place to find further clarification, surface any questions, and connect with other learners and Google experts. - 🎥 Daily Livestream Seminars and AMAs
We will go live everyday on Kaggle's YouTube channel, where the authors and course contributors will dive deeper into the topics and answer your burning questions. Plus, we've got fun surprises in store to keep the learning engaging. - 🆕 Capstone project
Level up your skills and build your portfolio with a real-world capstone project. Compete for prizes like Kaggle badges, swag and the recognition of being celebrated on Kaggle and Google’s social media channel. The capstone project will be launched on the last day of the event - November 14, 2025. Participation will be optional.
What’s being covered?
Day 1: Introduction to Agents & Agentic Architectures
Explore the foundational concepts of AI agents, their defining characteristics, and how agentic architectures differ from traditional LLM applications, laying the groundwork for building intelligent, autonomous systems.
Day 2: Agent Tools & Interoperability with MCP
Dive into the world of tools, understanding how AI agents can "take action" by leveraging external functionalities and APIs, and explore the ease of discovering and using tools offered by the Model Context Protocol (MCP).
Day 3: Context Engineering: Sessions, Memory Management
Explore how to build AI agents that can remember past interactions and maintain context. Learn how to implement short-term and long-term memory to create more robust agents capable of handling complex, multi-turn tasks.
Day 4: Agent Quality: Observability, Logging, Tracing, Evaluation, Metrics
Learn to build robust and reliable AI agents by mastering the critical disciplines of evaluating and improving agents. This session will cover observability, logging, and tracing to provide visibility, alongside key metrics and evaluation strategies to optimize agent performance.
Day 5: Prototype to Production
Go beyond local testing and learn to deploy and scale AI agents for real-world use. This session will cover the best practices for deploying your agents so that others can use them, including how to create a truly multi-agent system with the Agent2Agent (A2A) Protocol.
0 Comments