Welcome to the GDG Hackathon. In this fast-paced, 1-day in-person hackathon, you'll get hands-on with the most capable open models from Google. Your mission is to build an app that brings all Saint John community event listings into a single, seamless platform.
This hackathon is not about writing polished, production-ready code. It is a sprint to experiment, learn, break things, and build great solutions that benefit the Saint John community in just a few hours. You have access to the newly released Gemma 4 models. Team up, brainstorm a wild idea, hack a prototype, and pitch before the clock runs out. Bring your laptop, your boldest ideas, and let's build something amazing together!
In this track, participants will build an intelligent local AI agent designed to centralize community life in Saint John. Your goal is to leverage Google AI technologies to dynamically interact with external web sources, parse unformatted data, and present it in a single, unified local application.
The Challenge: Competitors should design their agents to target local community boards and event listings. For instance, your agent could target a live feed like Saint John Free Events, pull the raw web data, and use AI to automatically structure it into a clean, searchable user interface with custom headings and event synopses.
Winners will be judged on how effectively their agent uses tool orchestration or function calling to autonomously handle data retrieval, structure unformatted listings, and provide a seamless user experience for discovering local activities.
Tell a story. Show us the problem and how your Google AI application solves it in a powerful way for the Saint John community. While your technical execution is vital, the ability to communicate your vision through a compelling writeup and pitch is what will set the winners apart.
Prizes are awarded to the best overall projects in The Autonomous Agent Track that demonstrate exceptional vision, technical execution, and potential for real-world impact: - First Prize - Second Prize - Third Prize
Judges will evaluate submissions based on how effectively you utilize Gemma 4 models to build innovative and practical applications. Rather than expecting production-ready polish, judges will focus on the core functionality, creativity, and real-world impact of your prototypes. The official scoring rubric includes:
| Criteria | Description | Points |
|---|---|---|
| Google AI Integration (30%) | Did they effectively utilize Gemma 4? Is the model core to the solution? | 0-30 |
| Innovation & Impact (30%) | Does the app solve a meaningful problem? Is the approach creative and relevant? | 0-30 |
| Functionality (20%) | Does the prototype actually work? Is the demo convincing? | 0-20 |
| Presentation & Writeup (20%) | Is the Kaggle Writeup clear? Does it clearly explain the problem and solution? | 0-20 |