Education Track: Build Multi-Agent Systems with ADK

I built a multi-agent code review system for the Build Multi-Agent Systems with ADK track. Four specialized agents replace what would normally be one giant prompt. Each has a focused responsibility, and they pass work through a sequential pipeline deployed to Google Cloud Run.

What I Built

A web app that takes a GitHub repo URL and runs a full code review through four agents. Paste a link, and the pipeline takes over.

The flow: User → Planner → Security Scanner → Quality Gate → Archive & Verify → Audit Report

Each agent's output feeds into the next.…