Jie Xiang
Reliability engineer (6 yrs, commercial KVM cloud platform). Indie iOS dev (32 apps shipped solo via a multi-agent Claude Code pipeline). Now building at the intersection of cloud infrastructure and AI Agents.
What I ship
frexx.top
32 iOS apps on the App Store. All solo. All shipped through the same multi-agent pipeline.
prereviews.app
Pre-flight audit for App Store submissions. Free in-browser audit + Mac App with 60+ checks and AI second-pass.
apple-presubmit-audit
70+ App Store Review checks built from ~50 real rejections. CLI for indie iOS devs. Same engine that powers ShipReady.
Also open source
claude-agent-ledger
Per-subagent cost attribution for Claude Code. Reads the local JSONL session logs and shows what each subagent, model, and day actually consumed at marginal API rates. My own pipeline runs at ~$13K/week shadow cost on a $200/mo Max plan — the gap is the most interesting thing I've seen in LLM infra this year.
The thesis
AI Agents ship fast but break in the same long-tail ways distributed systems always have. Most teams don't yet have the eval, observability or reliability practices to catch it.
Six years of debugging a hypervisor at 3 AM gives you a reflex: if you don't have a per-component bill of materials, you don't actually understand the system. I'm pointing that reflex at AI Agents.