Building an Escalation Root-Cause Agent with Gemini and ADK

A customer service team lead at Amazon built an escalation root-cause analysis agent using Google's Agent Development Kit (ADK) and Gemini, deployed on Cloud Run. The agent automatically classifies escalation summaries, flags repeat patterns, and drafts coaching notes, aiming to scale manual review processes. The developer also created a batch runner script for processing CSV files of cases and plans to integrate with ticketing systems via MCP in the future.

Gen AI Academy APAC — Track 1 AI Agents with Gemini, ADK, and Cloud Run I lead a customer service team of 25 agents at Amazon, handling both buyer-side and marketplace seller support. A big part of my job is reviewing escalated cases — calls or chats where a customer asked for a supervisor — and figuring out why they escalated in the first place. Was it a policy gap? A training issue? A system limitation nobody flagged? Right now, that review is manual. Every escalation gets read, tagged, and turned into a coaching note by a human — usually me, or one of my leads. It works, but it doesn't scale well, and patterns across dozens of cases are easy to miss when you're reviewing them one at a time between everything else on your plate. So for Track 1 of the Gen AI Academy APAC program, I built an agent that does the first pass of this analysis automatically: read an escalation summary, classify the root cause against a standard taxonomy, flag whether it looks like a repeat pattern, and draft a coaching note — the same way I would, just faster and more consistently. The agent takes a case summary like this: Customer requested a refund for a damaged item outside the standard return window. Agent denied it citing policy; customer says a rep last month approved a similar exception for someone else. And returns a structured analysis: { "root cause category": "policy misapplication", "severity": "medium", "is likely repeat pattern": true, "pattern reasoning": "Inconsistent policy application across agents suggests a training or documentation gap rather than an isolated error.", "coaching note": "..." } It's built on Google's Agent Development Kit ADK with Gemini as the underlying model, and deployed as a live service on Cloud Run . The agent has one tool — a lookup function for the standard For batch review, I also built a runner script that processes a whole CSV of cases at once and outputs a summary report — closer to how I'd actually use this day to day, reviewing a batch of the week's escalations rather than one at a time. A few things stood out going through this: The repo includes a README.md with full setup instructions if you want to run it yourself, plus a sample CSV of synthetic escalation cases to test against no real customer data used anywhere in this project . The natural extension is Track 2 — instead of feeding it a CSV manually, connect it directly to a real ticketing system via MCP so it can pull escalations and analyze them without a manual export step. That's the version I'd actually want running against my team's queue. Built for the Google Cloud Gen AI Academy APAC program, in partnership with Hack2Skill.