The Challenge: Give Microservices an AI Upgrade

Supercharge an existing microservice application with agentic AI. You'll start with one of our pre-built applications—either the Bank of Anthos or the Online Boutique—and build on top of it.

The twist? You won't touch the core application code. Instead, you'll build new, containerized components that interact with the application's existing APIs. Think of it as building a smart, external brain that adds a whole new layer of intelligence.

Here's the tech you'll be working with:

Key technologies to be leveraged include:

• Required:

  • Google Kubernetes Engine (GKE): The chosen platform for deploying your enhanced microservice application and any new agentic components.

  • Google AI Models: Incorporate Google AI models, such as Gemini, to power your agentic functionalities.

• Optional:

  • Agent Development Kit (ADK): A strongly recommended (but not strictly required) toolkit for building your agents.

  • Model Context Protocol (MCP): Utilize MCP to connect and communicate with existing microservice APIs. You can deploy an MCP server on GKE alongside the application.

  • Agent2Agent (A2A) protocol: Explore how A2A can facilitate orchestration and communication between different agent components, enabling complex workflows.

  • Kubectl-ai: kubectl-ai acts as an intelligent interface, translating user intent into precise Kubernetes operations, making Kubernetes management more accessible and efficient.

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

What to Submit

• URL to the hosted Project (if available) for judging and testing, such as web UI, Chrome Extension, mobile app, etc. A hosted project is highly encouraged.
• Text description that summarizes the Project’s features, functionality, technologies used (GKE, ADK, MCP, A2A), information about any other data sources used, and your findings and learnings as you worked through the project
• URL to your public code repo to show how your project was built
• Architecture Diagram - show which technologies were used and how they interact with one another
• ~3-minute demo video 
• Optional Developer Contributions: 
  • Publishing a piece of content (blog, podcast, video): Covering how the project was built using GKE on any public platform (e.g., medium.com, dev.to, Youtube, etc.). You must include language that says you created the piece of content for the purposes of entering this hackathon. 
  • Publishing a social media post: Highlighting or promoting your project on social media post on X, LinkedIn, Instagram, or Facebook. For any social media posts on platforms such as X or LinkedIn, include the hashtag #GKEHackathon or #GKETurns10.

Check out the rules tab for full details on submissions.