Design patterns and production-ready architectures for building multi-agent AI systems with Google ADK.
# Build with ADK
**Learn to build production-ready AI agents with Google's Agent Development Kit**
A collection of real-world multi-agent examples built with [Google Agent Development Kit (ADK)](https://google.github.io/adk-docs/). Each agent demonstrates different ADK patterns and capabilities - from video generation to code execution.
---
## Featured Agents
### [Ad Campaign Agent](./ad-campaign-agent/)
<p align="center">
<a href="./ad-campaign-agent/">
<img src="ad-campaign-agent/assets/use-case-poster.jpeg" alt="Ad Campaign Agent" width="700">
</a>
</p>
Multi-agent platform for retail video advertising.
- **AI Video Generation** - Gemini + Veo 3.1 for professional ad content
- **Human-in-the-Loop** - Review and approval workflow
- **Analytics Dashboard** - In-store metrics with AI-generated charts
```bash
cd ad-campaign-agent && make install && make dev
```
---
### [Retail AI Location Strategy](./retail-ai-location-strategy/)
<p align="center">
<a href="./retail-ai-location-strategy/">
<img src="retail-ai-location-strategy/assets/images/main-intro-image.jpeg" alt="Retail AI Location Strategy" width="700">
</a>
</p>
Multi-agent pipeline for retail site selection.
- **Market Research** - Live data with Google Search integration
- **Competitor Mapping** - Geographic analysis with Google Maps API
- **Executive Reports** - Professional outputs with infographics and audio summaries
```bash
cd retail-ai-location-strategy && make install && make dev
```
---
### [Equity Research Agent](./adk-equity-deep-research/)
<p align="center">
<a href="./adk-equity-deep-research/">
<img src="adk-equity-deep-research/assets/use-case-poster.webp" alt="Equity Research Agent" width="700">
</a>
</p>
Multi-agent pipeline for professional equity research reports.
- **Human-in-the-Loop Planning** - User approval for research plans
- **Batch Chart Generation** - Agent Engine Sandbox for secure code execution
- **Multi-Market Support** - US, India, 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.