Testing journey - research, projects, conferences and article library

Michal Buczko - Quality Adventures

Subscribe

vibe coding

BowSmith, one feature, fully orchestrated: the case study

BowSmith, one feature, fully orchestrated: the case study

This is one feature in BowSmith, shipped end-to-end through Opus Max (architect) → Opus (orchestrator) → Sonnet (workers), with the numbers. Not a toy. A feature I'd have budgeted the better part of a week for if I'd built it by hand.

Quality at machine speed: ~70,000 tests, static analysis, and the review bias nobody warns you about

Quality at machine speed: ~70,000 tests, static analysis, and the review bias nobody warns you about

Quality at machine speed: ~70,000 tests, static analysis, and the review bias nobody warns you about

Where the three-tier stack was overkill: an honest retrospective

Where the three-tier stack was overkill: an honest retrospective

Not a victory lap the opposite. Where the stack was overkill, where the hand-off cost more than it saved, and the one-question filter I now run before I stand up the architect tier at all.

RPI → RPIQ: the method that made AI build production software

RPI → RPIQ: the method that made AI build production software

For the first stretch of this project I didn't have a method. I had a chat window, a vague plan, and a lot of optimism. It got me surprisingly far and then it fell over — not because the model wasn't capable, but because I wasn't giving it a system to be capable inside of.

The RPIQ loop: where the architect tier actually sits

The RPIQ loop: where the architect tier actually sits

That methodology is the loop I've been running long before any of these models existed: Research → Plan → Implement → Quality. RPIQ. This post maps the stack onto it — and shows why the mapping, not the model, is the thing worth keeping.

Orchestration Part3: Why I took the architect tier out of my delivery work on purpose

Orchestration Part3: Why I took the architect tier out of my delivery work on purpose

I pay for less AI than I could afford. On purpose. Two months ago I dropped the top tier from my subscription — the architect tier, the one with Opus Max in it. Not because it wasn't good. Because it was too good at being reached for.

CAST part3: Building the team: from 17 role-based agents to task-based Agent Teams

CAST part3: Building the team: from 17 role-based agents to task-based Agent Teams

Somewhere in Phase 4 of this build, my job changed. I stopped prompting an assistant and started managing a team — one you can't see, that never sleeps, and that will confidently agree with itself right off a cliff if you let it.