Ernie · AI-native full-stack engineer

I make AI-assisted engineering reliable.

An agent runs unattended exactly as far as you can verify its output — cheaply, deterministically, many times a night. I write about where that line falls, and build the guardrails that hold when every test passes and prod still goes down.

Open for long-term remote engagements and visa sponsorships.LinkedIn GitHub Telegram

Writing

Where AI autonomy breaks

2026·07·11I checked 57 repos whose CLAUDE.md bans the any type. One in eight turns the rule off.Of 57 public repos whose CLAUDE.md or AGENTS.md tells the coding agent never to use the any type, only 46% back the ban with a hard lint error; one in eight ships a config that sets the rule off. A hand-verified census, and a deterministic experiment showing why your CLAUDE.md is load-bearing precisely where it's redundant.2026·07·07A Claude Code Skill with 86k Stars Says It Cuts Tokens 65%. It Cut My Bill 1%.A wildly popular skill promises to cut your AI coding tokens by 65% by making the model talk like a caveman. It works — the model really does write less. But those words are about 1% of a real session, so your bill — or your subscription quota — barely moves. Why token counts aren't costs, and where the savings actually hide.2026·07·06Verification Is All You NeedAn AI agent runs unattended exactly as far as you can verify its output cheaply, deterministically, and many times a night. That line doesn't split backend from frontend — it cuts diagonally: CRUD is cheap to check, the concurrent backend and the rendered frontend are not. Design your autonomy around the gradient.2026·06·05Passed every test. Still took down prod.It passed every test and still took down prod — the bug wasn't a bad line, it was a state nobody enumerated. An LLM writes half your code now and nobody reads every line, so the state space is the only contract you can still enforce. A discriminated union deletes the bad states outright; a database constraint holds where the type can't reach. The two cheapest cuts — and the ones to make first.

All writing →

Background

The decade behind the thesis

Nine years building and shipping full-stack products — React and TypeScript on the front, Ruby on Rails and PostgreSQL behind them — and leading the engineering teams that ship them. I've scaled startups to eight figures in revenue and taken features from whiteboard to production as both an engineer and a technical lead.

The reliability and verification work is where I'm pointed now. The decade of shipping is what makes it credible.

Now

What I'm working on

Writing on the reliability of AI-assisted engineering — verification gradients, state-space design, and the guardrails that survive an agent you don't fully read.

I keep an opinionated, first-person AI-adoption playbook for teams — developers, designers, and support — covering the stack I actually run and where it breaks. Advising engagements in agentic development are opening up soon.

Appendix — the full stack, if you're curious

ShipReact · TypeScript · Next.js · Redux Toolkit · Ant Design · Shadcn · Ruby on Rails · PostgreSQL · Redis · Node.js · GraphQL · Elasticsearch · Docker · GitHub Actions · Vercel — nine years, startups scaled to eight figures.

VerifyState machines · covering arrays · model checking · property tests · database constraints

AgenticClaude Code · OpenAI Codex · Model Context Protocol · GitHub Spec Kit · Vercel AI SDK · Braintrust

NoteListed because they're real, not because they're the point. The point is upstairs.