In partnership with
Hi there,
If you missed it the first time - or you’ve just been watching AI agents from the sidelines - this is your rerun moment.
Google and Kaggle are relaunching their 5‑Day AI Agents Intensive from June 15-19, 2026, and it’s once again completely free, online, and built by the people actually working on this inside Google. Last time they ran this, over 1.5 million learners jumped in, and they’re clearly expecting an even bigger wave this round.
You’re not just watching talks. You’re getting:
Whitepapers to ground you in how modern AI agents really work.
Hands‑on code labs so you’re not just reading - you’re building.
Live sessions where you can ask Google engineers and researchers questions.
A Discord community packed with other builders working through the same material.
A capstone project so you walk away with something real you can show.
And yes: it’s free. No “7‑day trial,” no surprise paywall on day 3.
Fast browsing. Faster thinking.
Your browser gets you to a page. Norton Neo gets you to the answer. The first safe AI-native browser built by Norton moves with you from idea to action without slowing you down. Magic Box understands your intent before you finish typing. AI that works inside your flow, not beside it. No prompting. No copy-pasting. No switching apps.
Built-in AI, instantly and for free. Privacy handled by Norton. Built-in VPN and ad blocking protect you by default. No configuration. No extra apps. Nothing to think about.
Fast. Safe. Intelligent. That's Neo.
🛠️ What’s new this time?
This isn’t just a rerun of last year’s curriculum. Google and Kaggle are layering in some big upgrades that match where the ecosystem is headed.
Vibe coding workflows
You describe what you want to build in natural language, and the agents help generate the scaffolding, glue code, and workflows around it. That’s huge if you’re nervous about writing code or you just want to move faster from idea to prototype.More focus on scalable, high‑quality agents
The content leans harder into building agents you can trust: better evaluation, observability, and practical patterns for going beyond toy demos.“Graduate” your local agents to enterprise‑ready systems
There’s a new emphasis on taking the stuff you experiment with locally and turning it into governed, observable, production‑grade tools, capped with a brand‑new capstone project focused on that shift.
Under the hood, this builds on the original 5‑Day AI Agents Intensive they ran in November 2025, which covered agents, tools, memory, context, quality, and evaluation - now updated with vibe coding and more production‑minded patterns.
Who this is for (and why you should care)
You don’t need a CS degree for this. You don’t even need to think of yourself as “technical enough.” The whole point of vibe coding is to make “describe what you want, then steer” a first‑class way to build.
This is especially interesting if you’re:
A developer who wants to move from “I can call an API” to “I can ship full agentic systems that use tools, memory, and evaluation.”
A data scientist or ML engineer who wants to learn how to productionize agents instead of just playing with notebooks.
A founder or builder who has ideas for AI‑powered workflows but doesn’t want to write every line of boilerplate by hand.
A student or career‑switcher who wants something impressive to put in a portfolio or resume (the capstone project is perfect for that).
The time commitment is reasonable: five days, roughly 1–2 hours per day, with a mix of structured content and space to explore.
What you’ll actually learn
Based on the previous AI Agents Intensive and the new Google blog details, here’s the kind of ground they cover:
Core agent concepts: what makes an AI agent different from a basic LLM app.
Tools and APIs: how to let agents “take actions” in the real world by calling services, using the Model Context Protocol, and wiring up external tools.
Context & memory: sessions, short‑term memory, long‑term memory, and how to keep multi‑step workflows coherent.
Quality & reliability: evaluation strategies, logging, tracing, and observability so your agents don’t just “kind of work” - they’re measurable and improvable.
Vibe coding in practice: using natural language as your main interface to sketch flows, stitch tools together, and iterate quickly on ideas.
Capstone project: you’ll design and build a production‑style agent that can plug into real workflows, not just a demo chatbot.
By the end, you should be able to design, build, and deploy agents that look and feel like the tools everyone is talking about right now - with an actual project to point to.
10x the context. Half the time.
Speak your prompts into ChatGPT or Claude and get detailed, paste-ready input that actually gives you useful output. Wispr Flow captures what you'd cut when typing. Free on Mac, Windows, and iPhone.
🔥 How to join
You can find all the details and registration here on Google’s blog:
https://blog.google/innovation-and-ai/technology/developers-tools/kaggle-genai-intensive-course-vibe-coding-june-2026/
And the Kaggle page for the 5‑Day AI Agents Intensive / Vibe Coding course is here:
https://www.kaggle.com/competitions/5-day-ai-agents-intensive-vibecoding-course-with-google
Seats are free, but they’re treating this like a real program - structured content, live pieces, and a clear start/end - so it’s worth registering early and blocking the time on your calendar.
If you’ve been telling yourself “I’ll learn this agent stuff later,” this is a pretty strong sign from the universe to do it now.