What does the Industrial design firm — process as portfolio prompt produce?

A design website with Process photos, Material library, Project index, ISO line. The vibe target is "material-literate, process-proud, ISO-quiet" and the prompt body is printed in full on the page.

How well does it score?

91% average fidelity over 4 recorded runs. Best model: Claude 4.6 Sonnet. Weakest recorded run: 90% on GLM-4.6 (CN).

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: Morph Blob — open in library →

DesignFeaturedby Motif Studiopublished 2026-09-10

Industrial design firm — process as portfolio

vibe: material-literate, process-proud, ISO-quiet

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

prompt.txt — copy-paste ready

An industrial design firm's page where the process IS the portfolio — clients buy how the studio thinks.
• Process photos: three projects shown as sketch → clay / prototype → final, each stage a real photo with a caption on what was learned there ('the handle failed ergonomics testing at 0.4mm — the drawing shows the fix').
• Material library: a tactile grid of material samples (anodised aluminium, walnut, recycled PET felt) with honest notes on cost, lead time and where each belongs.
• Project index: past work as numbered rows — client category, discipline (industrial / packaging / UX), and the outcome in one line; no award walls, just shipped things.
• ISO line: quality and environmental certifications listed in a quiet footer band with what they actually certify.
• Working with us: 'we prototype by week two or we tell you why' — the studio's own SLA stated plainly.
• Palette: workshop neutrals, material greys, one orange used like a tool mark.

Stacks shipped:HTMLBlocks:Process photosMaterial libraryProject indexISO line

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 GLM-4.6 (CN) at 90/100 — ISO mentions understated correctly; process captions excellent.
All models built cleanly on the first pass.