# Agentic Studying
In November 2025, greater than 1.5 million folks signed up for a free course on constructing AI brokers. That is not a typo, and it isn’t a MOOC’s vainness metric for registrations that by no means convert: the identical cohort filed greater than 11,000 capstone submissions. Google and Kaggle’s 5-Day AI Brokers Intensive grew to become, by attendance, one of many largest technical programs ever run.
The excellent news for anybody who missed the stay week: all of it’s now free and self-paced, and there is much more to it than the hype steered.
# What It Really Is
The course is Google and Kaggle’s follow-up to their 2024 GenAI Intensive, which itself drew 140,000-plus builders and a rerun that set a Guinness document for the biggest digital AI convention. The 2025 version narrowed the main target from generative AI broadly to brokers particularly, which is the correct name given how a lot confusion nonetheless surrounds what an agent even is.
The stay run occurred over 5 days in November 2025, however the entire thing has since been remodeled right into a self-paced Kaggle Be taught Information, so now you can work by it by yourself schedule. A refreshed run, themed round vibe coding, additionally went out in June 2026 for individuals who want the cohort expertise. Both manner, the fabric is the draw.
# The 5 Days
Every day pairs a technical whitepaper with two hands-on codelabs constructed on Gemini and Google’s Agent Growth Package, so that you’re studying the idea after which instantly constructing it.
Day 1 – Introduction to brokers: Agent architectures and the basic query of when a job wants an agent in any respect versus a less complicated workflow. You construct your first agent and your first multi-agent system.
Day 2 – Instruments and interoperability with MCP: How brokers use instruments, easy methods to write customized ones, and the way the Mannequin Context Protocol (MCP) lets brokers discuss to exterior methods. Today additionally introduces human-in-the-loop approval for long-running operations, which is the distinction between a helpful agent and a harmful one.
Day 3 – Context engineering: Periods and reminiscence: Constructing stateful brokers that keep in mind, and giving them long-term reminiscence that persists throughout periods. That is the place most do-it-yourself brokers quietly crumble, so it is price slowing down right here.
Day 4 – Agent high quality: Logging, tracing, metrics, and evaluating each an agent’s responses and its software use. In case you take sooner or later severely, take this one. Measuring whether or not an agent works is the ability virtually no person teaches and everybody transport to manufacturing desperately wants.
Day 5 – Prototype to manufacturing: The agent-to-agent protocol and deploying to a managed runtime like Vertex AI Agent Engine. The unglamorous final mile between a pocket book that impresses your staff and a system actual customers can hit.
# Who Ought to Take It, and How you can Get the Most from It
In case you can write Python and you’ve got referred to as an LLM API, you are prepared. The course assumes programming literacy however not agent experience, which is precisely the band most practitioners sit in proper now.
One piece of recommendation from watching how these intensives are likely to go: do not skim the whitepapers to hurry to the code. The analysis and context-engineering materials on days three and 4 is the place the sturdy understanding lives, and it is the half you’ll be able to’t decide up later by copying a working repo. The codelabs educate you to construct an agent. The papers educate you why yours retains breaking.
The entire thing is free, it is obtainable now on Kaggle, and the capstone provides you one thing actual to level at if you’re executed. One million and a half folks discovered 5 days for it. Yours are in all probability price the identical.
Nahla Davies is a software program developer and tech author. Earlier than devoting her work full time to technical writing, she managed—amongst different intriguing issues—to function a lead programmer at an Inc. 5,000 experiential branding group whose purchasers embrace Samsung, Time Warner, Netflix, and Sony.
