From Vision to Production: the whole series, in one place
Over seven posts I wrote down how it actually happened: what worked, what it cost, and what failed. This is the map to all of it, so you can start wherever you want.
AI
Opus Max as architect: what actually changed when Fable went away
Opus Max as architect: what actually changed when Fable went away.
Short answer: less than you'd think — if you know what the tier is for.
The whole system on one page — live this week at CAST26
Week 7 (added — confirm before scheduling) of "From Vision to Production." Publishes Tue Aug 4, 2026.
If you're reading this, there's a decent chance you just heard me talk about it. Welcome — this post is the map. Six weeks of writing, and the eighteen
I lost my favourite tool and shipped faster anyway
Fable was the best tool in my stack. Then it went unavailable, and I had to give the architect seat to Opus Max on short notice.What I got was faster hand-offs. This is the post about why — and why I think losing the tool made the work better, not despite the constraint but because of it.
What failed, what it cost, and where this goes — the honest ledger
What failed, what it cost, and where this goes — the honest ledger
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
