I use Google Analytics to understand what gets read here. It only loads if you accept — nothing third-party runs before that. How Google uses this data
Learn to build with AI — from everyday life to production.
I share what I learn building with AI — from experiments that automate personal life with Claude Cowork to agentic development. Real trade-offs and open source for you to apply, whether in your routine or at your company. The goal is to help you build better — who writes it is a by-product, not the point.
Technical writing with explicit trade-offs · videos embedded in the text
The first post. Why this space exists, and what I'm promising you — the honest version of a mid-career transition into AI Engineering.
What you'll walk away withwhat this space is, and the four promises behind it.
Open source for you to study, clone and use. It grows as the automations graduate.
This site — a static React/Vite SPA, built in an agent-first loop with Claude Code.
A static SPA (no backend) served from S3 + CloudFront and provisioned with Terraform, delivered through an agent-driven SDLC: plan-first, blocking CI gates, deploy on merge. The repo is the source of truth.
What you take awayhow an agent-driven SDLC actually closes, from plan-first to deploy — and where to start reading the repo: the ADRs record every decision and the trade-off it cost.