Specific requirements

 

Cloud Run official documentation  

 

Learning resources

 

Other Resources

Request Form for Google Cloud Credits and GPU allocation

 
AI Agents

 

Agent Development Kit

Agent Development Kit (ADK) is a flexible and modular framework for developing and deploying AI agents.

  • ADK Docs - Deploy to GKE

  • ADK docs use the quickstart, checkout tools (function, built-in, GCP, MCP, OpenAPI, etc), use adk web locally and deploy.

  • ADK sample agents reference our agents or edit and use these as part of your multi-agent system.

  • ADK videos watch intros and deep dive videos to understand your options.

  • ADK github review the repo for more details and contribute with a PR.

 

Agent2Agent (A2A) Protocol

A2A is an open protocol enabling communication and interoperability between opaque agentic applications.

 

Model Context Protocol (MCP) 

MCP is an open protocol that standardizes how applications provide context to LLMs.

 

Gemini CLI 

Gemini CLI is a command-line AI workflow tool that connects to your tools, understands your code and accelerates your workflows.

 

FAQs 

How can I get Google Cloud credits for the hackathon?

  • You can obtain access to Google Cloud developer tools by signing up for a no-cost trial at cloud.google.com/free or by using an existing Google Cloud account and requesting $100 in Google Cloud credits by completing this form. Be aware that you are responsible for fees if your usage exceeds the credit amount.

How do I document and save my Prompts in AI Studio as required by the rules? 

  • If you are using the Chat function to create prompts within AI Studio, please use the share functionality to share the link with us when you submit.
  • If you are using the Build function, you can share the link to the app with us.

The requirements say “You should use the europe-west1 or europe-west4 region for your GPU workloads;“ what if I’m in another region? 

  • No matter where you’re located, please deploy your GPUs in these two regions.

Which tools and technologies are required for my project? 

You must build a NEW serverless application deployed on Google Cloud Run. 

  1. If you're building for the AI Studio category, your project must also use AI Studio and you must provide your prompts in your submission. 
  2. If you’re building for the AI Agents category, your project must also use Google ADK (Agent Development Kit).
  3. If you’re building for the GPU category, your project must also use GPUs to run an AI or ML model (like Gemma or similar).

What other technologies and tools can I use? 

  • As long as you're using the minimum requirements, you can use any extra tools or technologies you would like. While Cloud Run is the star, we encourage you to enhance your solutions by integrating with other technologies in the Google Cloud ecosystem:
  1. Foundation Models: We highly encourage the use of Gemini, Gemma, Imagen, and Veo.
  2. CLI-based AI Assistance: Use Gemini CLI to accelerate your development workflow.
  3. Google Cloud Services: Integrate with Cloud Storage, BigQuery, Firestore, and more!
  4. IoT & Mobile devices: Your Cloud Run application can power more than just web services!

Where can I find resources and support during the hackathon? 

  • Comprehensive resources can be found on the Resources tab. You can also register and watch the webinar which on October 28th at 9am PDT hosted by Google Cloud experts. Join the Devpost Discord server channels dedicated to this challenge.

How many bonus points can I get?

You can get a maximum of 0.4 points per optional contribution. You can get bonus point by: 

  1. The use of Google AI models: Including but not limited to models like Gemini, Gemma, Veo, etc

  2. Leveraging more Cloud Run services: points will be added if the project runs multiple services, need a front & back end 

Or by

  1. Publishing a piece of content (blog, podcast, video): Cover how the project was built using Cloud Run on any public platform (e.g., medium.com, dev.to, Youtube, etc.). The content must be public (not unlisted). You must include language that says you created the piece of content for the purposes of entering this hackathon.

  2. Publishing a social media post: Highlight or promote your project on a social media post on X, LinkedIn, Instagram, or Facebook. Include the hashtag #CloudRunHackathon.

These optional contributions are evaluated in Stage Three of the judging process. If the submission includes complete and requested optional developer contributions, points are added to the Stage Two Score.