谷歌推出25天AI Agents课程,作为 2025 年最昂贵圣诞节礼物!
# 25-Day AI Agents Course by Google A hands-on learning journey through Google's AI Agents capabilities. > **Official Course**: [Advent of Agents 2025](https://adventofagents.com/) - 25 days of Zero to Production-Ready AI Agents on Google Cloud ## About This Course This is Google Cloud's **Advent of Agents 2025** program - a 25-day journey to master AI Agents using: - **Gemini 3** - Google's latest AI models - **Agent Development Kit (ADK)** - Comprehensive agent development platform - **Agent Engine** - Production deployment infrastructure ### Course Highlights - 🎯 One feature per day, each taking less than 5 minutes to try - 📋 Copy-paste commands that work out of the box - 📚 Links to official documentation - 🆓 100% free > 📖 **Prerequisite**: [5-Day AI Agents Intensive Course](https://github.com/anxiong2025/5-Day-AI-Agents-Intensive-Course-with-Google) - Google's foundational course on AI Agents ### Difficulty Curve <p align="center"> <img src="assets/difficulty_curve.svg" alt="Course Difficulty Curve" width="600"> </p> ## Setup ### Prerequisites - Python 3.11+ - [uv](https://github.com/astral-sh/uv) package manager ### Installation ```bash # Install dependencies uv sync # Create .env file and add your API key cp .env.example .env # Edit .env and add your GOOGLE_API_KEY ``` ## Project Structure ``` . ├── day-01/ # Day 1: Introduction ├── day-02/ # Day 2: ... ├── ... ├── shared/ # Shared utilities │ ├── __init__.py │ └── config.py # Configuration helpers ├── pyproject.toml # Project dependencies └── README.md ``` ## Daily Progress | Day | Topic | Status | |-----|-------|--------| | 01 | Introduction to AI Agents | ✅ Done | | 02 | YAML Agent Configuration | ✅ Done | | 03 | Gemini Search Agent | ✅ Done | | 04 | Agent Engine Deployment | ✅ Done | | 05 | Telemetry & Tracing | ✅ Done | | 06 | ADK IDE Integration | ✅ Done | | 07 | Code Execution | ✅ Done | | 08 | Context Manageme
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.