Preview the prompt +
# Build brief — an original statement section in the taste of Speak
> Reference: [screenshot](https://uidiscovery.com/media/captures/speak/s-02.webp) (2880×684, 1440px viewport @2x) · UIDiscovery: https://uidiscovery.com/sections/speak-2 · source https://www.speak.com
## Goal
Build an original statement section for **[the user's brand]**. Its job: a large-type moment that sets tone and pace.
## Originality rules
- Never reuse Speak'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]).
## Layout
- Pattern: oversized typography with lots of space. Compact band (342px at 1440), own dark band #3748f7; no images (type-led); no interactive controls.
- Content slots: Heading (~7 words, like the reference); Body copy.
- Reference headline (tone/length only — never reuse): “Don't just learn languages, start speaking them”
- Responsive: stack columns below 768px keeping the order heading → body → action → visual; test at 390 / 768 / 1440px.
## Design tokens
- Colour: section background `#3748f7`, text `#242424` (2.5:1), accent `#1c49ff` (1.0:1), surface `#f5f5f5`, muted `#3748f7`. Keep the mood; swap the accent for the user's brand colour.
- Type: headings **Inter** (stand-in for Axiforma), body **Inter** (stand-in for Axiforma).
- Shape: Confident colour blocks — let full-bleed colour bands and big shapes carry the personality. Read exact corner radius, border and shadow treatment from the screenshots.
- Full tokens (CSS/Tailwind): https://uidiscovery.com/api/v1/sites/speak/tokens?format=tailwind
## Imagery
Best guess: mostly **photography** (light, cool, Education). 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 · Statement → photography
- Photography, seen in the capture (blue sky). (measured from the screenshot) Count: 1. Aspect: 4:5. Look first: [ref 1](https://uidiscovery.com/media/captures/speak/s-02.webp)
- **Stock** — “students studying together”: [Unsplash](https://unsplash.com/s/photos/students-studying-together?orientation=portrait) · [Pexels](https://www.pexels.com/search/students%20studying%20together/?orientation=portrait) · [Pixabay](https://pixabay.com/images/search/students%20studying%20together/?orientation=vertical)
- **Generate** — `Photograph: students studying together. Composition: simple composition with one focal point. Lighting: soft natural daylight, airy and high-key. Cool colour grade that sits on #3748f7, #1c49ff, #f5f5f5. 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.`
### 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 #1c49ff and #3748f7 on a #ffffff background. Lighting: soft natural daylight, airy and high-key; cool 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.`
- **illustration** — generate `Flat vector illustration: students studying together, friendly simplified shapes, limited palette of #3748f7, #1c49ff, #f5f5f5 plus one soft neutral, plenty of empty background, consistent line weight, cool mood. Aspect ratio 3:2. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.`
- **Licences:** check each stock image's licence page (Unsplash/Pexels licences, Pixabay Content License), credit when asked, avoid logos, brands and identifiable people; check your image model's commercial terms; never reuse the reference's own images or logos.
## 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.
- [ ] Originality: no copied logos, images, illustrations or copy from the reference; every image licensed or generated; credits recorded.
If you use Next.js + Tailwind: one server component for the section, next/image with explicit sizes, next/font for type, Tailwind v4 @theme tokens from the link above.
---
Whole-site brief: https://uidiscovery.com/api/v1/brief?slug=speak · MCP `get_design_brief({ id: "speak-2" })`, `get_image_plan({ id: "speak-2" })`. Cite the reference as https://uidiscovery.com/sections/speak-2.
