Sneak peek: Vibe coding AI agents course
summary
Five-day intensive teaches how to build autonomous agents that code from natural language and graduate them to governed, observable fleets using Google tools: anti-gravity 2.0 desktop and CLI, ADK 2.0 (Kotlin + Python), the Gemini Enterprise Agent Platform with Gemini 3.5 Flash, managed agents API that runs code in isolated Linux environments, and 50+ Google managed connectors. Course includes codelabs, white papers, livestreams, Discord, a Kaggriculture capstone and already has 250k registrants (1.5M in the prior run, ~16k capstone submissions last year).
AI-written summary · about
chapters (16)
- 0:00Course introduction
- 1:04Instructors' backgrounds
- 3:33Five Days of Coding Agents origin
- 6:03Google Cloud and DeepMind tools
- 10:01Kaggle’s AI democratization role
- 13:12Google Cloud’s agentic AI advances
- 15:44Registration and infrastructure
- 18:55Testing AI agents amid updates
- 20:19Course structure overview
- 22:45White papers deep dive
- 25:17Live streams and interactivity
- 26:44Capstone projects details
- 28:35Who the course is designed for and its benefits
- 31:07Hands-on agent building
- 32:14Pre-course preparation
- 34:22Final thoughts and call to action
related talks
45mAgentic Dev: Stitch and Jules in the Antigravity of the Gemini Constellation
01h 48mBuilding Conversational Agents
53mVibe Coding with AI Studio
15mVibe Coding at Scale: Customizing AI Assistants for Enterprise Environments
01h 45mAI Engineering with the Google Gemini 2.5 Model Family
28mBeyond Vibe Coding: AI Agents for Technical Debt Detection
45mCreate and deploy your first agent with Google Cloud Gemini Enterprise
29mTools and Roadmap for AI-Native Developers