Building in the open.
Insights on AI-era operations, web production, and what it actually looks like to build a company with one founder and AI.
The Bootstrap Paradox: Why Every System Needs Something It Can't Create
Every system has a component that must exist before the system that produces it can run. This isn't a bug in your architecture — it's the seed everything else grows from.
When AI Workflows Start Fixing Themselves
A stress test rejected its own premise. A publishing task discovered pipeline gaps. Within hours, the system spawned fixes for its own failures. What happens when AI workflows have structured checkpoints — and why self-healing matters more than speed.
When Parallel AI Agents Start Catching Each Other's Gaps
Two AI sessions ran independently. Neither knew the other existed. One flagged a gap the other was already fixing. What happens when parallel AI agents produce structured outputs — and why emergent cross-checking matters more than speed.
When Your Contracts Start Fixing Themselves
A task specification executes, discovers a gap, and that gap becomes a new specification that fixes it. Nobody designed this. It emerged from two structural decisions: mandatory findings sections and an owner review loop.
When Your Diagnostic Tool Finds What You Didn't Know
You build a tool to check for problems. You run it once. It immediately finds something you've been staring past for months. That's not a bug — that's the entire point.
My AI Cofounder Ran 6 Parallel Sessions While I Thought
A solo founder's Thursday morning — designing architecture while AI agents execute, review, and refine in parallel. What delegation looks like in the AI era.
The Beautiful Absurdity of Modeling Your Company in Java
What happens when a founder with a CS background treats their company like a codebase — and the compiler catches organizational bugs.
Why Every Founder Should Learn to Think in Types
You don't need to write code. You need to think in types. What does your company own? What does it produce? What must it never touch?
What AI Can't Do: The Irreducible Floor of Human Judgment
Counter-narrative to 'AI replaces everything.' Five things that permanently stay human — and why that's a design principle, not a limitation.
Measuring AI-Augmented Output: What Matters and What Doesn't
Practical metrics for anyone trying to measure whether AI is actually helping. Most people measure the wrong thing.
The Solo Founder's Effort Curve: How AI Changes the Math
How one founder's effort-to-output ratio changed over three months of AI-augmented work. Real progression, no hype. The curve bends when you shift from doing to orchestrating.
Introducing AccelMars Mind: The Missing Layer for AI-Powered Development
AI CLIs are powerful but stateless. Every session starts from scratch. Here's what we're building to fix that — and why the methodology will be free.
Vietnam's Technical Talent: What Foreign Companies Get Wrong
Vietnam has exceptional engineering talent. But most foreign companies access it wrong — hiring junior teams through agencies instead of partnering with senior leaders who know both worlds.
What Swiss Banking Taught Me About Software Quality
When bugs mean compliance violations and downtime means financial penalties, you learn a different kind of engineering. Here's how enterprise constraints shaped how I build software today.
Building AccelMars: One Founder + AI
What it actually looks like to build a real company with one founder and AI agents. No theory — real decisions, real products.
Why Solo Founders Need an Ops Platform
You're running 10 business functions with 15 disconnected apps. There's a better way — and it starts with seeing yourself as the CEO you actually are.