The ventures I run, and what I shipped for others.

Every pattern published here ran in one of these first. The ventures are the lab; the client work is the proof it travels.

Ventures

Built and operated by me

DVNC Dev

Live

An AI engineering venture, run in public by an AI CEO.

Role
Founder, chairman
Market
United States
Year
2026
Status
Live, autonomous
  • AI Engineering
  • Autonomous Agents
  • Infrastructure
Case study
DVNC Dev

DVNC Studio

Live

Campaign-grade creative, built with AI, owned by you.

Role
Founder, creative director
Market
United States
Year
2026
Status
Live
  • Creative
  • Film
  • Brand
Case study
DVNC Studio
A withlida property analysis article
The withlida developers section
The withlida areas section

Breath Diagnostics

Live

The website for an FDA-breakthrough lung-cancer screening company.

Client
Breath Diagnostics, Inc.
Sector
Medical technology
Year
2026
Role
Website design & build
  • Website
  • Design & Build
  • Healthcare
Case study
Breath Diagnostics

Equedia

Live

15,000 pages moved off WordPress, republished in nine languages.

Client
Equedia Network Corporation
Sector
Investing media
Year
2026
Role
Migration & platform
  • Migration
  • Internationalization
  • Publication
Case study
Equedia
Latest.
Railway Alternatives in 2026: Render, Fly.io, Northflank, Heroku and More

Railway Alternatives in 2026: Render, Fly.io, Northflank, Heroku and More

Compare Railway alternatives for services, Postgres, workers and cron, with current starting prices, secrets handling and a staged migration checklist.Oct 22, 2026Build
Gumloop Review

Gumloop Review

Gumloop reviewed for lead research, scraping, documents and email: a step-by-step setup, current credits, approval controls and alternatives.Oct 22, 2026Build
Synthetic Data Generation: LLM Training and Test Data

Synthetic Data Generation: LLM Training and Test Data

Generate LLM evals, fine-tuning examples and test fixtures with a worked recipe, filtering, deduplication, human checks and provider terms.Oct 22, 2026Build
RLHF Explained: Human Feedback, DPO and Fine-Tuning

RLHF Explained: Human Feedback, DPO and Fine-Tuning

How RLHF turns human rankings into model behavior, how DPO and verifiable rewards differ, and which preference fine-tuning APIs a small company can use.Oct 22, 2026Build
Model Router: How LLM Routing Works and How to Test It

Model Router: How LLM Routing Works and How to Test It

Learn how LLM model routing works, compare documented options, and test quality with a support-app example, cost formula, and held-out eval set.Oct 21, 2026Build
Semantic Caching: How It Works and When to Reuse Answers

Semantic Caching: How It Works and When to Reuse Answers

Understand semantic caching, its four-step lookup, and how thresholds, expiry and user scope prevent similar questions from receiving the wrong answer.Oct 21, 2026Build
Pydantic AI vs LangChain

Pydantic AI vs LangChain

Choose a Python agent framework with matching ticket-triage code, validated outputs, LangGraph workflows, tracing, evals and migration guidance.Oct 21, 2026Build
Zed vs Cursor 2026: Editing Feel, Agents and Teamwork

Zed vs Cursor 2026: Editing Feel, Agents and Teamwork

Zed vs Cursor for developers: compare editing feel, agents, model choice, collaboration and the limits of switching or using both.Oct 21, 2026Build

Need a plan, not just the reading? The Intensive turns sprawl into a 30-day shipping map.

  1. 01Pre-work systems audit
  2. 02Live working day
  3. 0330-day priority map
  4. 0414-day async follow-up
Book the Intensive$5,000 virtual · $12,000 in person (Dubai) · Limited slots each month
Newsletter

One letter, every Sunday.Working systems, not hot takes.

Weekly. No spam. Unsubscribe anytime.