5-Day AI Agents Intensive Course with Google
by Kaggle & Google
Google's free five-day agent intensive — whitepapers, codelabs, podcasts and recorded livestreams taking you from agent architectures to production.
Overview
The 5-Day AI Agents Intensive Course with Google originally ran live November 10–14, 2025 and is now available on Kaggle as a self-paced Learn Guide, with the whitepapers, companion podcasts, codelabs and recorded livestreams all accessible after the fact. It was crafted by Google's own AI researchers and engineers, with Anant Nawalgaria (Senior Staff Machine Learning Engineer and founder of the GenAI Intensive) leading. The curriculum covers agent architectures, tools, memory and evaluation, and moving from prototype to production, and each day blends deep dives with hands-on codelabs plus live discussion on Discord and YouTube livestreams with Google experts. Participants in the live cohorts could also apply their skills to a capstone project. The course is explicitly pitched at a wide range of learners — 'whether you're just starting out or advancing your expertise' — and its live November 2025 run was one of the largest technical courses ever run by attendance. A refreshed June 2026 run themed around vibe coding followed, extending the material toward natural-language-first agent development workflows.
At a Glance
- Topic
- Agentic
- Level
- All Levels
- Format
- Course
- Cost
- Free
- Duration
- 5 days, self-paced
- Provider
- Kaggle & Google
- Hands-on
- Yes — code/exercises
- Certificate
- None
What You’ll Learn
- ✓Choose and reason about agent architectures for a given problem
- ✓Give agents tools and wire them to APIs and external systems
- ✓Design agent memory so multi-step and multi-turn behavior holds up
- ✓Evaluate agents systematically rather than eyeballing outputs
- ✓Take an agent prototype through to a production-ready system
- ✓Practice each concept in hands-on codelabs alongside the whitepapers
Highlights
- •Free, and written by the Google researchers and engineers who build these systems
- •Self-paced Learn Guide bundles whitepapers, codelabs, companion podcasts and recorded livestreams
- •One of the largest technical courses ever run by attendance in its live November 2025 cohort
- •Capstone project for applying the full stack of material
- •Refreshed in June 2026 with a vibe-coding-focused run
Who It’s For
Best For
- ✓Developers building their first production agent
- ✓AI engineers wanting a structured, vendor-authored agent curriculum
- ✓Practitioners who learn best from whitepaper-plus-codelab pairings
- ✓Teams standardizing on a shared vocabulary for agent architecture and evaluation
Prerequisites
- •Basic Python
- •Familiarity with calling LLM APIs helps but is not required
- •A free Kaggle account to access the Learn Guide materials
FAQ
What is 5-Day AI Agents Intensive Course with Google?
A free five-day intensive on building AI agents, crafted by Google's own AI researchers and engineers and now published on Kaggle as a self-paced Learn Guide. Suited to developers at any level who want a structured path from agent architectures and tool use through memory, evaluation and production deployment.
Is 5-Day AI Agents Intensive Course with Google free?
5-Day AI Agents Intensive Course with Google is free to access.
What level is 5-Day AI Agents Intensive Course with Google for?
5-Day AI Agents Intensive Course with Google is aimed at a all levels audience. Recommended background: Basic Python, Familiarity with calling LLM APIs helps but is not required, A free Kaggle account to access the Learn Guide materials.
How long does 5-Day AI Agents Intensive Course with Google take?
Expect roughly 5 days, self-paced. Most learners work through it at their own pace.
What will I learn from 5-Day AI Agents Intensive Course with Google?
You'll learn: Choose and reason about agent architectures for a given problem; Give agents tools and wire them to APIs and external systems; Design agent memory so multi-step and multi-turn behavior holds up; Evaluate agents systematically rather than eyeballing outputs; Take an agent prototype through to a production-ready system; Practice each concept in hands-on codelabs alongside the whitepapers.