Preview the prompt +
# Build brief — an original marketing website in the taste of Together AI
> Reference: https://www.together.ai · UIDiscovery: https://uidiscovery.com/sites/together-ai · captured 2026-09-21 at a 1440px desktop viewport (+ 390px iPhone shots) · [full page](https://uidiscovery.com/media/captures/together-ai/full.webp) · [scroll video](https://uidiscovery.com/media/captures/together-ai/preview.mp4)
## 1. Goal
Build an original marketing website for **[the user's brand]** that feels as considered as Together AI — 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 Together AI: structure, rhythm, hierarchy, palette mood and type pairing.
- Never reuse Together AI'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
- Together AI (together.ai): AI marketing website, dark.
- 7 sections: Hero → Features → Content → Features → Content → Call to action.
- Spacing: about a screen per idea (median section ≈870px).
- Hero headline: 8 words — short and punchy; keep yours under ~9.
- Type: one family (The Future). Imagery: mostly product UI screenshots/mockups, 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. Half to one screen (724px at 1440), own light band #ffffff; 116 image elements (icons, logos, product UI — not 116 photos); 3 buttons (tabs, toggles or per-card actions).
- Slots: Eyebrow / announcement pill (optional); H1 (~8 words, like the reference); Supporting line, 1–2 sentences; Primary + secondary action; Hero visual (see image plan).
- Topic (tone/length only — never reuse): “Build what's next on the AI Native Cloud”
- [Screenshot](https://uidiscovery.com/media/captures/together-ai/s-01.webp) · imagery: slot 1
### 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. Half to one screen (635px at 1440), own light band #ffffff; 3 image/graphics; 3 buttons (tabs, toggles or per-card actions).
- Slots: Section title (~4 words, like the reference); 3 items: icon or visual + short title + 1–2 line description; Primary + secondary action.
- Topic (tone/length only — never reuse): “The Together AI Platform”
- [Screenshot](https://uidiscovery.com/media/captures/together-ai/s-02.webp) · imagery: slot 1
### 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. About one full screen (1052px at 1440), own light band #ffffff; 47 image elements (icons, logos, product UI — not 47 photos); 18 buttons (tabs, toggles or per-card actions).
- Slots: Section title (~3 words, like the reference); 3 items: icon or visual + short title + 1–2 line description; Primary + secondary action.
- Topic (tone/length only — never reuse): “Full-stack cloud”
- [Screenshot](https://uidiscovery.com/media/captures/together-ai/s-03.webp) · imagery: slot 1
### 4. Content — supporting content that deepens one idea.
- Layout: text + media block. About one full screen (870px at 1440), own dark band #010120; 87 image elements (icons, logos, product UI — not 87 photos); 83 buttons (tabs, toggles or per-card actions), 162 links (link lists / navigation).
- Slots: Heading (~4 words, like the reference); Body copy; Supporting visual (see image plan); Primary + secondary action.
- Topic (tone/length only — never reuse): “Grounded in cutting-edge research”
- [Screenshot](https://uidiscovery.com/media/captures/together-ai/s-04.webp) · imagery: slot 1
### 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. About one full screen (883px at 1440), own light band #ffffff; 8 images/icons (a set of cards or a small gallery); one primary button.
- Slots: Section title (~6 words, like the reference); 8 items: icon or visual + short title + 1–2 line description; One primary action.
- Topic (tone/length only — never reuse): “AI natives build on Together AI”
- [Screenshot](https://uidiscovery.com/media/captures/together-ai/s-05.webp) · imagery: slot 2
### 6. Content — supporting content that deepens one idea.
- Layout: text + media block. About one full screen (800px at 1440), own light band #ffffff; 4 images/icons (a set of cards or a small gallery); primary + secondary button.
- Slots: Heading (~5 words, like the reference); Body copy; Supporting visual (see image plan); Primary + secondary action.
- Topic (tone/length only — never reuse): “What’s new at Together AI”
- [Screenshot](https://uidiscovery.com/media/captures/together-ai/s-06.webp) · imagery: slot 3
### 7. Call to action — close the page with one clear next step.
- Layout: short headline + one primary action on a contrasting band. Tall, ≈1.5 screens (1347px at 1440), own light band #ffffff; 44 image elements (icons, logos, product UI — not 44 photos); one primary button, 36 links (link lists / navigation).
- Slots: Headline (~5 words, like the reference); One sentence of support; One primary action.
- Topic (tone/length only — never reuse): “Start building on Together AI”
- [Screenshot](https://uidiscovery.com/media/captures/together-ai/s-07.webp) · imagery: slot 1
Inner pages also captured (Pricing, Product, Customers, About, Sign up, Blog, Docs, Careers, Contact, Shop): https://uidiscovery.com/sites/together-ai?view=pages
## 5. Design system
### Colour
| Role | Hex | Use | Contrast on background |
|---|---|---|---|
| background | `#000000` | page background | — |
| foreground | `#ffffff` | body text, headings | 21.0:1 |
| accent | `#ffffff` | none captured — monochrome. Primary buttons invert (foreground fill, background text); add your brand colour only for small highlights | — |
| surface | `#010120` | cards, inputs, alternate bands | text on it 20.5:1 |
| muted | `#ffffff` | secondary text, borders | 21.0:1 |
Captured palette: `#000000` `#ffffff` `#010120`. Section bands top→bottom: `#ffffff` → `#010120`. Roles are assigned automatically — sanity-check them against the screenshot. Keep the palette's *mood* (dark, neutral, desaturated) and proportions; swap the accent for the user's brand colour.
### Tokens
```css
:root {
--background: #000000;
--foreground: #ffffff;
--accent: #ffffff;
--surface: #010120;
--muted: #ffffff;
--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 The Future. “The Future” 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 ≈870px tall at 1440 (median; range 635–1347px, 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 2 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. Dark-first; for a light mode swap background ↔ foreground, lighten the surface, keep the accent and re-check contrast.
## 6. Imagery plan
Best guess: mostly **product UI screenshots/mockups**, some photography (dark, neutral, desaturated, AI). Inferred from element counts, colours and industry — not from the pixels — so open the linked screenshots and match the real style before sourcing anything.
### Slot 1 · 1. Hero, 2. Features, 3. Features, 4. Content, 7. Call to action → product UI (uncertain)
- AI sections with many image elements — most likely product UI screenshots/mockups plus icons. Count: one consistent treatment across these sections. Aspect: 3:2. Look first: [ref 1](https://uidiscovery.com/media/captures/together-ai/s-01.webp) [ref 2](https://uidiscovery.com/media/captures/together-ai/s-02.webp) [ref 3](https://uidiscovery.com/media/captures/together-ai/s-03.webp) [ref 4](https://uidiscovery.com/media/captures/together-ai/s-04.webp)
- **Stock** — “laptop blank screen minimal desk”: [Unsplash](https://unsplash.com/s/photos/laptop-blank-screen-minimal-desk?orientation=landscape) · [Pexels](https://www.pexels.com/search/laptop%20blank%20screen%20minimal%20desk/?orientation=landscape) · [Pixabay](https://pixabay.com/images/search/laptop%20blank%20screen%20minimal%20desk/?orientation=horizontal)
- **Generate** — `Product-shot backdrop for a UI screenshot: smooth dark gradient from #000000 to #010120 with a soft #ffffff glow behind the centre, subtle floor shadow, empty centre area where a screenshot will be placed. Lighting: low-key, moody directional light with deep shadows. Aspect ratio 3:2. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people. No UI elements.`
- Build the UI itself in HTML/CSS with realistic sample data from YOUR product (or screenshot your real app). Don't generate UI as an image and don't reuse the reference's screenshots. Stock/AI is only for the backdrop or device frame.
### Slot 2 · 5. Features → photography
- Photography, seen in the capture (people). (measured from the screenshot) Count: a set of ~8 in one consistent style. Aspect: 4:3. Look first: [ref 1](https://uidiscovery.com/media/captures/together-ai/s-05.webp)
- **Stock** — “3d glass shapes render close up dark”: [Unsplash](https://unsplash.com/s/photos/3d-glass-shapes-render-close-up-dark?orientation=landscape) · [Pexels](https://www.pexels.com/search/3d%20glass%20shapes%20render%20close%20up%20dark/?orientation=landscape) · [Pixabay](https://pixabay.com/images/search/3d%20glass%20shapes%20render%20close%20up%20dark/?orientation=horizontal)
- **Generate** — `Photograph: 3d glass shapes render close up. Composition: tight crop, identical framing and background across the whole set. Lighting: low-key, moody directional light with deep shadows. Neutral, desaturated colour grade that sits on #ffffff, #010120. 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 · 6. Content → illustration (uncertain)
- Light AI section with a few graphics — illustration, icon art or a product shot. Count: a set of ~4 in one consistent style. Aspect: 4:5. Look first: [ref 1](https://uidiscovery.com/media/captures/together-ai/s-06.webp)
- **Stock** — “technology flat illustration”: [Unsplash](https://unsplash.com/s/photos/technology-flat-illustration?orientation=portrait) · [Pexels](https://www.pexels.com/search/technology%20flat%20illustration/?orientation=portrait) · [Pixabay](https://pixabay.com/images/search/technology%20flat%20illustration/?orientation=vertical)
- **Generate** — `Flat vector illustration: abstract gradient mesh, friendly simplified shapes, limited palette of #ffffff, #010120 plus one soft neutral, plenty of empty background, consistent line weight, neutral, desaturated mood. Aspect ratio 4:5. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.`
- Uncertain: this could equally be photography, a product shot or icon art — open the reference screenshots and match what you see.
### 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, glossy glass-like shapes and a smooth gradient in #ffffff and #010120 on a #000000 background. Lighting: low-key, moody directional light with deep shadows; neutral, desaturated tone. Minimal and calm, generous negative space on one side for text. Aspect ratio 3:2. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.` · stock: [“abstract dark gradient 3d” on Unsplash](https://unsplash.com/s/photos/abstract-dark-gradient-3d?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/together-ai/tokens · kit https://uidiscovery.com/api/v1/sites/together-ai/kit · MCP `get_design_brief({ slug: "together-ai" })`, `get_image_plan({ slug: "together-ai" })`. Cite the reference as https://uidiscovery.com/sites/together-ai.
