What does the Watch atelier — precision as storytelling prompt produce?

A craft website with Macro hero, Movement cutaway, Finish swatches, Service promise. The vibe target is "macro-precise, quiet, spec-first" and the prompt body is printed in full on the page.

How well does it score?

90% average fidelity over 4 recorded runs. Best model: Claude 4.6 Sonnet. Weakest recorded run: 89% on Codex.

Are failures included?

No build failures are recorded for this prompt, and the log says so rather than implying every model succeeded elsewhere.

Concept render — composed live from this prompt's palette & layout. Reproducible with the library, not a stock screenshot.

Concept scene: Grid Drift — open in library →

CraftFeaturedby Motif Studiopublished 2026-09-10

Watch atelier — precision as storytelling

vibe: macro-precise, quiet, spec-first

starter — 4 blocks, 1 stack≈ 700 tokens to run (estimate)

prompt.txt — copy-paste ready

A watch atelier page where macro photography does the selling and every claim is a spec, not a superlative.
• Hero: full-bleed macro of the dial at 2:1 with the model name in a quiet serif; a one-line 'what makes this one different' (a regulator dial, a five-day reserve) instead of 'luxury for the discerning'.
• Movement cutaway: an annotated diagram of the calibre with each part named in plain English — 'the part that stops the second hand from stuttering'.
• Finish swatches: rows of finishing options (sunray, matte, brushed) rendered as actual swatch tiles you can compare side by side.
• Provenance: the caseback story in three scenes — where the movement is assembled, who regulates it, how long each piece waits for its final timing test.
• Service promise: 'every watch, every five years' with honest turnaround and what a service actually includes.
• Palette: near-black, brushed silver, one muted accent; typography does the precision work other sites fake with gradients.

Stacks shipped:HTMLBlocks:Macro heroMovement cutawayFinish swatchesService promise

Community:▶ Re-run this prompt ⤴ Submit a remix of it ★ Your saved listRe-runs are a labelled simulation; the run log on this page is the real record.

⚠ Before you run it, know this

Lowest score was Codex at 89/100 — Solid; provenance scenes strong, hero copy drifted once on pass two.
All models built cleanly on the first pass.