Case study · AI engineering

ADA: an AI agent for checkout support operations

ADA is a technical support agent for checkout operations. It is not a chatbot bolted onto a help centre: it is an agent wired into the engineering and observability tools the team already used, answering operational questions and investigating incidents with authenticated, read-only access.

Context

I worked on a checkout and payments platform where the same operational questions came back every week: is this payment method failing for merchant X, did that order really fail, is this behaviour caused by a feature flag. The answers existed, but they were spread across tools with different auth models and different query languages: observability (Sentry, Grafana, Prometheus, Loki), product analytics (Mixpanel), feature flags (GrowthBook), issue tracking (Linear), Slack and a set of operational runbooks.

Engineers were spending part of their day being a search engine across six dashboards.

Problem

My responsibility

I developed ADA: the agent service, the tool integrations, and the permission model that decides what the agent is allowed to read.

What I implemented

How it works

A request arrives from Slack. The agent plans which tools to call, calls them through the authenticated tool layer, and composes an answer from the returned evidence. Because the tools are read-only and scoped, the worst consequence of a bad tool choice is a useless query, not a production change. The same service is reused by a scheduled job that produces the daily per-merchant digest.

Design decisions and trade-offs

Result

Roughly 70% fewer support tickets reaching the development team after ADA started handling operational questions and first-pass incident triage.

What I learned