February 20, 2026
Builder mode vs architect mode in AI development
Most AI dev workflows assume you’re executing a resolved plan. Real product work is architectural discovery — and specs should be the output, not the input.
Systems-thinking
February 25, 2026
How I maintain coherence across 66,000 lines of code without losing the thread
Most AI-augmented development workflows break when they crash into the context wall.
February 28, 2026
Building four products in parallel while holding a full-time job — the system, not the hustle
This is not a productivity post. I'm not going to tell you to wake up at 5am.
February 28, 2026
Why I went the opposite direction from spec-first
Spec-first tools aren’t wrong — they just don’t match how everyone thinks. SR-SI supports an architect’s workflow: sketch, test, refine, repeat, without context loss.
February 28, 2026
The architect and the builder
AI can accelerate execution, but its bigger advantage is accelerating discovery. The question is whether you’re using AI to follow plans, or to find better ones.
March 5, 2026
Architect mode is a superpower, and it's exhausting
If you’re the person who turns chaos into clarity, you’ll end up carrying more than your role. Architect mode is a tool — not an obligation.
March 6, 2026
Building multiple products without marketing yet
A full-time job can create the cleanest product environment: honest decisions, optionality, and time to follow real signals. In the AI era, system-thinking generalists gain a structural edge.
March 6, 2026
The zoom problem and fractal navigation
Most tools force you to choose between the map and the detail. Fractal navigation solves the zoom problem by letting every node contain a full map without collapsing the gestalt.
May 12, 2026
The memory problem
The first SR-SI lesson was not that AI needed more intelligence. It needed a better way to orient itself before it worked.
May 13, 2026
The retro lie: why your sprint retrospective never finds the real problem
Retrospectives often surface symptoms, not causes. Coordination failures usually begin upstream, long before the sprint where the visible problem appears.