Preview the prompt +
# Build brief — an original marketing website in the taste of Duolingo
> Reference: https://www.duolingo.com · UIDiscovery: https://uidiscovery.com/sites/duolingo · captured 2026-09-21 at a 1440px desktop viewport (+ 390px iPhone shots) · [full page](https://uidiscovery.com/media/captures/duolingo/full.webp) · [scroll video](https://uidiscovery.com/media/captures/duolingo/preview.mp4)
## 1. Goal
Build an original marketing website for **[the user's brand]** that feels as considered as Duolingo — same structure, rhythm and polish, entirely new identity and content.
## 2. Originality rules
- Build an ORIGINAL design for the user's own brand in the same *taste* as Duolingo: structure, rhythm, hierarchy, palette mood and type pairing.
- Never reuse Duolingo's logo, name, product imagery, illustrations, icons, screenshots or copy. Write new copy for the user's product.
- If the user hasn't said what their product is, ask first (or use clearly marked placeholders like [Brand], [Product], [Audience]).
- Reference screenshots are for looking at, not for embedding or tracing.
## 3. The taste, in short
- Duolingo (duolingo.com): Education marketing website, light.
- 11 sections: Hero → Features → Statement → Content → Features → Statement → Footer.
- Spacing: about a screen per idea (median section ≈827px).
- Hero headline: 10 words — a full sentence; keep yours to one thought.
- Type: one family (Duolingo sans). Imagery: mostly typography with little or no imagery, some photography.
## 4. Page structure (top to bottom)
### 1. Hero — state what the product is and for whom in one glance, and offer the primary action.
- Layout: headline-led stack: eyebrow → H1 → supporting line → actions, with a visual beside or below. About one full screen (900px at 1440), page background; 48 image elements (photo collage/gallery + small graphics); primary + secondary button, 44 links (link lists / navigation).
- Slots: Eyebrow / announcement pill (optional); H1 (~10 words, like the reference); Supporting line, 1–2 sentences; Primary + secondary action; Hero visual (see image plan).
- Topic (tone/length only — never reuse): “The most fun way to learn languages, chess, and more!”
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-01.webp)
### 2. Features — explain the key benefits, grouped so each can be scanned in seconds.
- Layout: section title over a grid or alternating rows of benefit items. Tall, ≈1.9 screens (1700px at 1440), own light band #ddf4ff; no images (type-led); no interactive controls.
- Slots: Section title; 2 items: icon or visual + short title + 1–2 line description.
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-02.webp)
### 3. Features — explain the key benefits, grouped so each can be scanned in seconds.
- Layout: section title over a grid or alternating rows of benefit items. Half to one screen (530px at 1440), page background; 1 image/graphic; 1 text link instead of buttons.
- Slots: Section title (~3 words, like the reference); 3 items: icon or visual + short title + 1–2 line description; Text link action.
- Topic (tone/length only — never reuse): “free. fun. effective.”
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-03.webp)
### 4. Features — explain the key benefits, grouped so each can be scanned in seconds.
- Layout: section title over a grid or alternating rows of benefit items. Half to one screen (530px at 1440), page background; 1 image/graphic; no interactive controls.
- Slots: Section title (~3 words, like the reference); 3 items: icon or visual + short title + 1–2 line description.
- Topic (tone/length only — never reuse): “backed by science”
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-04.webp)
### 5. Features — explain the key benefits, grouped so each can be scanned in seconds.
- Layout: section title over a grid or alternating rows of benefit items. Half to one screen (530px at 1440), page background; 1 image/graphic; no interactive controls.
- Slots: Section title (~3 words, like the reference); 3 items: icon or visual + short title + 1–2 line description.
- Topic (tone/length only — never reuse): “stay motivated”
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-05.webp) · imagery: slot 1
### 6. Features — explain the key benefits, grouped so each can be scanned in seconds.
- Layout: section title over a grid or alternating rows of benefit items. Half to one screen (530px at 1440), page background; 1 image/graphic; no interactive controls.
- Slots: Section title (~3 words, like the reference); 3 items: icon or visual + short title + 1–2 line description.
- Topic (tone/length only — never reuse): “personalized learning”
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-06.webp) · imagery: slot 2
### 7. Statement — a large-type moment that sets tone and pace.
- Layout: oversized typography with lots of space. Tall, ≈1.4 screens (1289px at 1440), page background; 4 images/icons (a set of cards or a small gallery); 2 text links instead of buttons.
- Slots: Heading (~3 words, like the reference); Body copy; Supporting visual (see image plan); Text link action.
- Topic (tone/length only — never reuse): “learn anytime, anywhere”
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-07.webp)
### 8. Content — supporting content that deepens one idea.
- Layout: text + media block. About one full screen (900px at 1440), own dark band #100f3e; 3 image/graphics; one primary button.
- Slots: Heading; Body copy; Supporting visual (see image plan); One primary action.
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-08.webp)
### 9. Features — explain the key benefits, grouped so each can be scanned in seconds.
- Layout: section title over a grid or alternating rows of benefit items. Half to one screen (722px at 1440), page background; 1 image/graphic; 1 text link instead of buttons.
- Slots: Section title (~3 words, like the reference); 3 items: icon or visual + short title + 1–2 line description; Text link action.
- Topic (tone/length only — never reuse): “duolingo english test”
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-09.webp)
### 10. Statement — a large-type moment that sets tone and pace.
- Layout: oversized typography with lots of space. About one full screen (853px at 1440), page background; 2 image/graphics; 1 text link instead of buttons.
- Slots: Heading (~5 words, like the reference); Body copy; Supporting visual (see image plan); Text link action.
- Topic (tone/length only — never reuse): “learn a language with duolingo”
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-10.webp) · imagery: slot 3
### 11. Footer — navigation, legal and contact — the page's index.
- Layout: multi-column link groups, brand line, legal row. About one full screen (827px at 1440), own light band #58cc02; no images (type-led); 67 links (link lists / navigation).
- Slots: Brand mark + one-line description; 3–5 link columns; Newsletter or contact (optional); Legal row + social icons.
- [Screenshot](https://uidiscovery.com/media/captures/duolingo/s-11.webp)
Inner pages also captured (Sign up, Docs, Enterprise, Contact, Security): https://uidiscovery.com/sites/duolingo?view=pages
## 5. Design system
### Colour
| Role | Hex | Use | Contrast on background |
|---|---|---|---|
| background | `#ffffff` | page background | — |
| foreground | `#100f3e` | body text, headings | 18.1:1 |
| accent | `#58cc02` | primary buttons, links, highlights — sparingly | 2.1:1 ⚠ not for text; use as a fill with #111111 text (9.0:1) |
| surface | `#ddf4ff` | cards, inputs, alternate bands | text on it 15.9:1 |
| muted | `#777777` | secondary text, borders | 4.5:1 — borders / large text only |
Captured palette: `#ffffff` `#58cc02` `#ddf4ff` `#100f3e` `#777777` `#4b4b4b`. Section bands top→bottom: `#ffffff` → `#ddf4ff` → `#100f3e` → `#58cc02`. Roles are assigned automatically — sanity-check them against the screenshot. Keep the palette's *mood* (light, natural, earthy) and proportions; swap the accent for the user's brand colour.
### Tokens
```css
:root {
--background: #ffffff;
--foreground: #100f3e;
--accent: #58cc02;
--surface: #ddf4ff;
--muted: #777777;
--font-heading: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-body: "Inter", ui-sans-serif, system-ui, sans-serif;
--radius: 12px; /* calibrate from the screenshot */
}
/* Tailwind v4 — in globals.css after @import "tailwindcss"; */
@theme {
--color-background: var(--background);
--color-foreground: var(--foreground);
--color-accent: var(--accent);
--color-surface: var(--surface);
--color-muted: var(--muted);
--font-heading: var(--font-heading);
--font-sans: var(--font-body);
}
```
### Typography
- Headings: **Inter** (Google Fonts) — reference uses Duolingo sans. “Duolingo sans” is likely a custom or licensed face. Inter is a neutral stand-in — pick a closer free match by eye from the screenshot.
- Body: same family — a single-family system; create contrast with size and weight, not a second face.
- Scale (starting point, sizes weren't measured — calibrate against the 1440px screenshot): display clamp(2.5rem, 5vw, 4.25rem), h2 clamp(1.75rem, 3vw, 2.5rem), h3 1.25rem, body 1rem–1.125rem / 1.6, small 0.875rem. Headings: tight tracking (-0.02em), line-height 1.05–1.15.
### Spacing & rhythm
Sections run ≈827px tall at 1440 (median; range 530–1700px, captures cap at 1700px) — roughly a screen per idea. Start with 96–120px vertical padding per section on desktop and about two-thirds of that on mobile. The background changes 5 times down the page — use band changes to mark chapters. 8px spacing grid, 1200–1280px max content width, 24px (mobile) / 32–48px (desktop) gutters.
### Shape, depth & theme
Radii and shadows weren't measured. Read exact corner radius, border and shadow treatment from the screenshots. Light-first; for a dark mode use a near-black (not #000) background, ~90% white text, lift surfaces with lightness not shadow, re-check the accent.
## 6. Imagery plan
Measured from 9 section screenshots: mostly **typography with little or no imagery**, some photography (light, natural, earthy, Education). Still glance at the linked screenshots to match the exact mood.
### Slot 1 · 5. Features → photography
- Photography, seen in the capture (frozen, liquid, water). (measured from the screenshot) Count: 1. Aspect: 4:3. Look first: [ref 1](https://uidiscovery.com/media/captures/duolingo/s-05.webp)
- **Stock** — “notebook and laptop on desk close up”: [Unsplash](https://unsplash.com/s/photos/notebook-and-laptop-on-desk-close-up?orientation=landscape) · [Pexels](https://www.pexels.com/search/notebook%20and%20laptop%20on%20desk%20close%20up/?orientation=landscape) · [Pixabay](https://pixabay.com/images/search/notebook%20and%20laptop%20on%20desk%20close%20up/?orientation=horizontal)
- **Generate** — `Photograph: notebook and laptop on desk close up. Composition: tight crop, identical framing and background across the whole set. Lighting: soft natural daylight, airy and high-key. Natural, earthy colour grade that sits on #ffffff, #58cc02, #ddf4ff. Photorealistic, natural textures, shallow depth of field, 35mm lens. Aspect ratio 4:3. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.`
### Slot 2 · 6. Features → photography
- Photography, seen in the capture (recreation, sport, winter sport). (measured from the screenshot) Count: 1. Aspect: 4:3. Look first: [ref 1](https://uidiscovery.com/media/captures/duolingo/s-06.webp)
- **Stock** — “library bookshelf light close up”: [Unsplash](https://unsplash.com/s/photos/library-bookshelf-light-close-up?orientation=landscape) · [Pexels](https://www.pexels.com/search/library%20bookshelf%20light%20close%20up/?orientation=landscape) · [Pixabay](https://pixabay.com/images/search/library%20bookshelf%20light%20close%20up/?orientation=horizontal)
- **Generate** — `Photograph: library bookshelf light close up. Composition: tight crop, identical framing and background across the whole set. Lighting: soft natural daylight, airy and high-key. Natural, earthy colour grade that sits on #ffffff, #58cc02, #ddf4ff. Photorealistic, natural textures, shallow depth of field, 35mm lens. Aspect ratio 4:3. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.`
### Slot 3 · 10. Statement → photography
- Education references lean on photography. Count: a set of ~2 in one consistent style. Aspect: 4:5. Look first: [ref 1](https://uidiscovery.com/media/captures/duolingo/s-10.webp)
- **Stock** — “students studying together wide shot”: [Unsplash](https://unsplash.com/s/photos/students-studying-together-wide-shot?orientation=portrait) · [Pexels](https://www.pexels.com/search/students%20studying%20together%20wide%20shot/?orientation=portrait) · [Pixabay](https://pixabay.com/images/search/students%20studying%20together%20wide%20shot/?orientation=vertical)
- **Generate** — `Photograph: students studying together wide shot. Composition: simple composition with one focal point. Lighting: soft natural daylight, airy and high-key. Natural, earthy colour grade that sits on #ffffff, #58cc02, #ddf4ff. Photorealistic, natural textures, shallow depth of field, 35mm lens. Aspect ratio 4:5. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.`
- **No imagery (type-led)** — 1. Hero, 2. Features, 3. Features, 4. Features, 7. Statement, 8. Content, 9. Features: No imagery needed — type, spacing and colour do the work. If the screenshot shows a background graphic, rebuild it in CSS (gradient, grid, noise) or a short muted video, not a stock photo.
- **Icons** — 11. Footer: Use one open-source icon set at one stroke weight — Lucide, Phosphor or Heroicons (MIT) — tinted with the text or accent token. Social icons: Simple Icons.
### If the screenshots show a different style
Open the refs first and name what you actually see (photo / product UI / illustration / abstract gradient or 3D / type only). If it differs from the guess, switch routes — UI is built in code, type-only needs no image, otherwise:
- **abstract 3D / gradient** — generate `Abstract 3D render: soft, matte clay shapes and a smooth gradient in #58cc02 and #777777 on a #ffffff background. Lighting: soft natural daylight, airy and high-key; natural, earthy tone. Minimal and calm, generous negative space on one side for text. Aspect ratio 16:9. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.` · stock: [“abstract gradient 3d” on Unsplash](https://unsplash.com/s/photos/abstract-gradient-3d?orientation=landscape) (same query works on Pexels/Pixabay)
- **illustration** — generate `Flat vector illustration: students studying together, friendly simplified shapes, limited palette of #ffffff, #58cc02, #ddf4ff plus one soft neutral, plenty of empty background, consistent line weight, natural, earthy mood. Aspect ratio 16:9. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.` · stock: [“education flat illustration” on Unsplash](https://unsplash.com/s/photos/education-flat-illustration?orientation=landscape) (same query works on Pexels/Pixabay)
- **Licences:** Unsplash and Pexels images are free for commercial use under their own licences; Pixabay under the Pixabay Content License. Check each image's page before use, credit the photographer when asked (good practice anyway), and skip images showing logos, trademarks, branded products or identifiable people without a release.
- **AI generation:** the prompts work with any image model (GPT Image, Imagen, Flux, Midjourney, Firefly, SDXL…) — check its commercial-use terms. Never put the reference brand's name or “in the style of <brand>” in a prompt.
- **Never** download, trace or re-host the reference's own images, illustrations, product shots or logos.
## 7. Build steps
1. Confirm brand, product, audience and the primary action with the user.
2. Set up the tokens (CSS variables / Tailwind @theme) and load the fonts.
3. Build the sections in order, mobile-first, with each reference screenshot open.
4. Write original copy for every slot — match length and tone, never the words.
5. Source every image via the imagery plan (stock or generated); compress it and record credits.
6. Run the checklist at 390 / 768 / 1440px and fix what fails.
## 8. Acceptance checklist
- [ ] Responsive at 390px, 768px and 1440px — no horizontal scroll, tap targets ≥ 44px on mobile.
- [ ] Colour contrast WCAG AA: 4.5:1 body text, 3:1 large text and UI; visible focus states; full keyboard navigation.
- [ ] Semantic HTML: one <h1>, ordered headings, landmarks (header/nav/main/footer), labelled form fields, alt text on meaningful images.
- [ ] Performance: modern image formats with width/height set, lazy-load below the fold, ≤ 2 font families with font-display: swap, LCP < 2.5s.
- [ ] prefers-reduced-motion respected; animations under ~300ms and never blocking content.
- [ ] Originality: no copied logos, images, illustrations or copy from the reference; every image licensed or generated; credits recorded.
## 9. If you use Next.js + Tailwind
Paste the @theme block into globals.css, load fonts with next/font/google, make each section a server component in components/sections/, use next/image with explicit sizes, and keep client components for interactive bits only (menus, toggles, accordions).
---
More: tokens https://uidiscovery.com/api/v1/sites/duolingo/tokens · kit https://uidiscovery.com/api/v1/sites/duolingo/kit · MCP `get_design_brief({ slug: "duolingo" })`, `get_image_plan({ slug: "duolingo" })`. Cite the reference as https://uidiscovery.com/sites/duolingo.
