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.
I break down why convention over configuration matters more once agents are writing code, and why the real bottleneck shifts from generation to review. I also walk through the Rails primitives that make agent-written apps easier to maintain, from Active Job and Action Mailer to migrations, tests, and the quality gates that define done.
Need senior technical guidance?
As a fractional CTO, I help teams make confident architecture and AI integration decisions.
View services
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.
3. Building CreatorSignal: From Report to Refinement (LIVE)
This stream picks up where the last one left off. CreatorSignal is an idea validation tool for YouTube creators: you submit a video concept, a research agent
Get new videos and posts by email
Weekly videos on AI engineering, plus deeper dives in the newsletter.
Occasional emails, no fluff.