5-Day AI Agents: Intensive Vibe Coding Course With Google
Overview
- day1
Summary
Day0 ; Brief summary of how the course works & How to setup
In this section, we includes a brief summary of how the course works and detailed instructions on how to get set up.
How the Course Works
The course is designed to be flexible and interactive, allowing you to learn at your own pace while benefiting from live sessions and community engagement(kaggle).
- Daily Content Release: New assignments will be posted in the discussion forums each day, your primary source for all course materials.
- Assignment Notifications (Fast Follow): Given the large number of participants, links to all assignment materials including whitepapers, codelabs and podcast episodes will also be shared on the Kaggle Discord and sent via follow-up email shortly after being posted. You can find the codelabs FAQs here.
- Support & Discussion: Join the discussion on our dedicated Discord channels to connect with other learners, ask questions, and get support from Google researchers and engineers who’ll be monitoring the channels throughout the week.
- Daily Livestreams: Join Anant Nawalgaria and Smitha Kolan live each day starting Monday, June 15th at 11 AM PT / 8 PM CEST / 11:30 PM IST on Kaggle's Youtube Channel. They’ll be joined by special guests from Google. After each session, recordings will be shared on Kaggle's Discord.
- Course Completion: To get the most out of this intensive, we recommend completing all course materials including whitepapers, podcasts and codelabs at your own pace.
- [Optional] Capstone Project: On the final day, you’ll have the chance to apply everything you’ve learned by building your own AI agent. By participating in the capstone project, you’ll earn a badge and certificate on Kaggle.
Setup Instructions:
To ensure you’re ready for the course, please complete these essential setup steps:
- **Kaggle Account:**Sign up for a Kaggle account.
- **AI Studio Account:**Sign up for an AI Studio account and ensure you can generate an API key.
- Download and install:
- **Kaggle Discord:**Sign up for a Discord account and join us on the Kaggle Discord server. We've set up dedicated channels for event discussions and learnings.
- Please note that if you’d like to post on other channels on the Kaggle discord you’ll need to link your Kaggle account to discord here.
Once you have everything set up, please introduce yourself in the #5dgai-introductions channel on Discord.
Day1「Introduction to Agents & Vibe Coding」
成果物
課題
- Listen to the summary podcast episode for this unit.
- To complement the podcast, read "The New SDLC with Vibe Coding" whitepaper.
- Complete these codelabs:
- Get started with Antigravity 2.0 and IDE
- Build a Web Application in AI Studio and Deploy to Cloud Run
- Tomorrow at 11:00 AM PT, Anant Nawalgaria and Smitha Kolan will host the first livestream on Kaggle's YouTube channel. They'll be joined by codelabs author Fran Hinkelmann, along with other special guests from Google: Jamie de Guerre, Logan Kilpatrick, Parthasarathy Ranganathan, and Shubham Saboo to discuss the assignments and share insights.
Code Labでのinsights
まず、2つのコードラボの共通点は、「Vibe Coding を体験すること
🎒 Day 1 Assignment
Complete Unit 1 – "Introduction to Agents & Vibe Coding"
- Listen to the summary podcast episode for this unit.
- To complement the podcast, read "The New SDLC with Vibe Coding" whitepaper.
- Complete these codelabs:
- Get started with Antigravity 2.0 and IDE
- Build a Web Application in AI Studio and Deploy to Cloud Run
💡What You'll Learn
Today's whitepaper talks about the transition from manual syntax coding to intent-driven "vibe coding" and disciplined "agentic engineering." It explores how AI agents compress the traditional software development life cycle (SDLC) and explains the "factory model" where developers act as system orchestrators who design the evaluation, constraint, and context harnesses that safely guide autonomous execution.
In the codelabs, you'll familiarize yourself with Antigravity 2.0, the Antigravity IDE, and the Antigravity CLI to vibecode your first applications. You'll also use Google AI Studio to deploy your app to Cloud Run, enabling you to share your vibe coded app with your friends.
Day 2 Assignment
Complete Unit 2 – “Agent Tools & Interoperability(ツールと相互運用性)”
- Listen to the summary podcast episode for this unit.
- To complement the podcast, read the "Agent Tools & Interoperability" whitepaper.
- Complete these codelabs:
- Get started with Antigravity CLI
- Explore Google Developer Knowledge MCP server in Google Antigravity
💡 What You'll Learn
Today's whitepaper talks about standardizing the plug-and-play AI ecosystem using open protocols to eliminate the complex technical debt of custom tool integrations. It details how the Model Context Protocol (MCP) connects models to data sources, outlines Agent2Agent (A2A) collaboration, showcases Agent-to-User Interface (A2UI) for generative UI, and introduces Agent Payments Protocol (AP2) and Universal Commerce Protocol (UCP) for secure machine-to-machine commerce.
Day2 のホワイトペーパーでは以下を学びます。
- カスタムツール統合の複雑な技術的負債を解消するために、open protocolsを使用して plug-and-play AI ecosystemを標準化することについて説明しています。
- 具体的には、以下を取り扱います。
- how the Model Context Protocol (MCP) connects models to data sources
- outlines Agent2Agent (A2A) collaboration
- showcases Agent-to-User Interface (A2UI) for generative UI
- introduces Agent Payments Protocol (AP2) and Universal Commerce Protocol (UCP) for secure machine-to-machine commerce.
コードラボで学ぶことは以下です。
- how to add MCP servers to Antigravity, giving it access to the canonical, machine-readable source of Google's public developer documentation. You'll then extend your familiarity with Antigravity by using it via the terminal with Antigravity CLI.
- AntigravityにMCPサーバーを追加し、Googleの公開開発者向けドキュメントの正規の機械可読ソースにアクセスできるようにする方法を学びます。その後、Antigravity CLIを使用してターミナル経由でAntigravityを操作することで、Antigravityの操作方法をさらに習得します。
Day2
Codelab1「Antigravity CLI を使った実践演習」
詳細はこちらのリンクを参照。
学べること
Antigravity CLI とその機能について学び、いくつかのユースケースに適用できるようになる。
具体的な学習内容は以下のとおりです
- Antigravity CLI のインストールと構成
- macOS | Linux
curl -fsSL https://antigravity.google/cli/install.sh | bash
Windows PowerShellirm https://antigravity.google/cli/install.ps1 | iex
Windows CMDcurl -fsSL https://antigravity.google/cli/install.cmd -o install.cmd && install.cmd && del install.cmd - agy --version
- agy で起動しGoogle アカウントでログインする
- Antigravity CLI の基本的な使用方法を理解する
- Antigravity CLI を使用したユースケースの探索
要点
以下、重要な点やTips をまとめました。
- Antigravity CLI とは?
- Antigravity の軽量なターミナルユーザーインターフェース(TUI)サーフェス
- Antigravity と同じコア エージェント機能(マルチステップ推論、マルチファイル編集、ツール呼び出し、会話履歴など)をターミナルに直接提供するもの
CLIインストール完了画面

この Codelab は、初心者を含むあらゆるレベルのユーザーとデベロッパーを対象としています。この Codelab のユースケースは、デベロッパー タスクとデベロッパー以外のタスクに分類されています。デベロッパーのユースケースでは、Antigravity CLI を使用してコードをバイブさせ、GitHub リポジトリを使用して、コードの説明/理解、ドキュメントの生成、問題の修正などの一般的な開発タスクを実行する方法を示します。この Codelab では、これらのユースケースを完了することをおすすめします。最後に、デベロッパー以外のユーザーを対象とした日常的なタスクをいくつか紹介する省略可能なセクションがあります。
リファレンス ドキュメント
マンチカン航海士の知恵袋
マンチカン航海士が記事全文を読んでいるニャ... 🐾