1. Building CreatorSignal: Rails Auth & Deploy from Scratch (LIVE)
I built a Rails app from scratch using only Claude Code as my AI coding partner. Here’s the full, unedited session showing my real workflow for AI-augmented development.
In this live coding session, I start a brand new Ruby on Rails SaaS app and build user authentication from zero using Claude Code. But this isn’t a “how to build auth in Rails” tutorial. It’s a deep look at how I actually use Claude Code to drive development: plan mode, custom skills, TDD workflows, iterating on Claude’s memory, sub-agent code reviews, and more.
Need senior technical guidance?
As a fractional CTO, I help teams make confident architecture and AI integration decisions.
View services
Rails Gives AI Agents What They Actually Need
Rails gives AI agents what most stacks don't: conventions, strong defaults, and less custom infrastructure to verify.
The Engineering Headcount Math Just Broke
AI coding agents broke the old headcount-equals-output math. Small senior teams now outship larger orgs, and verification is the new bottleneck.
Treat Your AI Agent Like a New Engineer
Most AI coding agent failures are not prompt problems. They are onboarding problems.
Your Codebase Is the Problem, Not the AI Model
When AI agents don't follow your team's conventions, the instinct is to fix the prompt or switch models. The real bottleneck is usually the codebase itself.
Get new videos and posts by email
Weekly videos on AI engineering, plus deeper dives in the newsletter.
Occasional emails, no fluff.