What does the Architecture atelier — selected works prompt produce?

A architecture website with Studio hero, Selected works, Method note, Contact rail. The vibe target is "structural, precise, editorial" and the prompt body is printed in full on the page.

How well does it score?

90% average fidelity over 3 recorded runs. Best model: Claude 4.6 Sonnet. Weakest recorded run: 88% 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: Aurora Veil — open in library →

ArchitectureVerifiedby Motif Studiopublished 2026-09-14

Architecture atelier — selected works

vibe: structural, precise, editorial

starter — 4 blocks, 2 stacksany viewport≈ 270 lines generated (estimate)≈ 600 tokens to run (estimate)

prompt.txt — copy-paste ready

An architecture atelier portfolio: a studio hero with the practice name in large serif and one line of method ("we build slowly and measure twice"), selected works as a grid where each entry carries its real metrics (site, year, area) in tabular figures, a method note in three short paragraphs, and a contact rail with the studio address and hours — no invented client logos, no award lists the studio did not win. Bone and ink, one structural accent, hairline rules. Work cards carry a hover lift; colours are CSS variable tokens; reduced-motion disables the lift.

Palette tokens:#f4efe6#262016#5a6472#8a6d3b

Remix this brief: