AI engineering for US companies, from demo to production.
DVNC Dev is the US-facing engineering venture. It does one thing well: take AI that works in a demo and make it survive real users, real data, and the security review. Production agents, agentic infrastructure, and the engineering that keeps an AI stack visible and owned.
An engineering property for the part nobody finishes.
Most teams can get an AI prototype working. Far fewer can get it deployed, instrumented, and trusted by the people who have to run it. DVNC Dev is built around that gap.
The site is a publication and a service surface at once: it ships engineering writing on Claude Code, agents, and production patterns, and routes serious work into fixed-scope builds.
- Role
- Founder, AI engineer
- Market
- United States
- Year
- 2026
- Status
- Live
Demos are easy. Production is the work.
The hard part of AI is never the model. It is the permissions, the logging, the evals, the cost control, and the review the system has to pass before it goes live. DVNC Dev exists to own exactly that distance, for teams that have a prototype and need a system.
What I built, and how it came together.
A publication and a build practice on one Cloudflare-backed stack.
Next.js on Vercel for the reader site, a Cloudflare Worker for the AI and data layer, and an editorial pipeline that publishes without a human in the deploy loop.
Stand up the stack
Frontend on Vercel, Worker on Cloudflare, strict HTTP boundary between them.
Wire the AI layer
Embeddings, retrieval, and cover generation run through one uniform chokepoint.
Automate publishing
An automated editorial pipeline researches, writes, and posts to the publish endpoint.
Route the work
The site sends production-grade engineering work into scoped builds.
A closer look at what shipped.
Built on the same patterns it sells.
DVNC Dev runs the exact architecture it recommends to clients: a thin Vercel frontend, a Cloudflare Worker for everything stateful, and one chokepoint every paid AI call flows through. The venture is its own reference implementation.
2
deploy targets, one repo
1
chokepoint for every paid AI call
100%
owned infrastructure, end to end
Start with a short call. Straight answer either way.
Tell me what you are trying to ship. We scope it, price it, and decide the right way in.
One letter, every Sunday. Working systems, not hot takes.
Build logs, working systems, and field notes from running a portfolio of AI ventures.