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.
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.
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.
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.