# Trust feature card with source citations

Schema: Design Details SECTION.md v3.2
Website: Parallel
Source: https://parallel.ai/
Source section IDs: 21c49f6f-7734-465b-a473-5acd17520930
Status: AI analysed; vocabulary promotion is automated

## Builder's note

What makes it work:
- The mockup shows the product claim itself: highlighted phrases in a text snippet map to citation cards, each with a confidence bar, so the idea reads in seconds.
- Two clean columns, with heading, paragraph and one button on the left and nested cards on the right, give a clear reading order and generous whitespace inside 80px section padding.
- Small mono uppercase labels against a calm white canvas, soft grey borders and a pale blue surface keep the mockup quiet, so the colour-coded highlights carry the emphasis.

What a screenshot can't show:
- The recording showed no motion and no browser animations, so nothing here is known to animate or respond to hover.
- Labels like HIGH CONFIDENCE are 12px mono at weight 500, with 18px line height and -0.2px letter spacing; gaps between elements are tight at 6 to 8px, with 48px between larger blocks.

Borrow: Make the mockup demonstrate the claim with believable real data, linking each highlight to its evidence by colour.
Leave alone: Don't copy the orange action colour, the pale blue surface, the proprietary mono typeface (use a free mono such as JetBrains Mono instead) or the Berners-Lee/CERN example content.

## Classification

- Type: feature-card
- Layout: Left side text and button; right side UI mockup graphic.
- Styles: minimal, soft
- Confidence: 95%

## Purpose and structure

A feature card illustrating source citations and confidence scores within a text snippet.

Visual signature: Text snippet with colorful highlight markers and progress bars underneath denoting confidence.

## Components

- heading
- paragraph
- button
- ui mockup
- data visualization

## Typography

- Display: gerstnerProgramm — 36px 500
- Heading: gerstnerProgramm — 32px 500
- Body: gerstnerProgramm — 16px 500
- Mono: ftSystemMono — 13px 400

## Functional palette

- Canvas: canvas #FFFFFF
- Text: text #181818
- Primary-Action: primary action #FB631B
- Muted-Text: muted text #858483
- Border: border #E5E5E5
- Surface: surface #E9F0F5
- Accent: accent #FF743D

## Motion evidence

- No section-specific authored motion was established.

## Section quality

Overall: 62.71/100 (Good)
Scored coverage: 85%

- Typography: 62 — Clear type hierarchy with heading, body, mono labels for toggle/citations, and consistent weight contrast; nothing beyond competent execution of a standard system. Next tier: No distinctive type personality or scale play beyond standard heading/body/mono split used sitewide.
- Composition: 65 — Clean two-column layout (text/CTA left, mockup right) with a well-organized nested card system (snippet, toggle, three citation sub-cards) that reads with clear visual order and generous whitespace. Next tier: Layout is a conventional feature-split pattern; the mockup card grid, while tidy, doesn't introduce a novel structural idea to push past polished-familiar territory.
- Motion: not_assessed — No motion_moments or animation data supplied; deterministic animation list is empty. Next tier: Needs timestamped evidence of any visible animated state change to assess.
- Content: 68 — The mockup directly visualizes the product claim (citations with confidence scores) using real example data (Tim Berners-Lee, CERN, 1989), making content and visual tightly integrated and legible as a concept demo. Next tier: Content illustrates the feature competently but doesn't add an unexpected narrative layer or interactive depth cue beyond a static labeled mockup.
- Originality: 58 — Color-coded highlight-to-citation-card mapping with progress bars is a reasonably specific device, but highlight+badge+progress-bar patterns for 'confidence' are common in AI-product marketing. Next tier: Lacks a signature visual mechanic unique to this brand; the pattern is recognizable from many AI trust/provenance sections elsewhere.
- Adaptability: 60 — Grid-based layout with discrete card components (snippet box, toggle, three citation cards) is modular and the deterministic token data (radius, border, spacing, colors) is well specified, making skin/structure separation feasible. Next tier: Lacks specified interaction/responsive behavior data (e.g., how cards reflow or toggle state changes) to fully decouple behavior from structure.

Strengths:
- Mockup directly demonstrates the stated product claim with concrete example data
- Clear three-tier hierarchy: heading/copy, UI snippet, and citation detail cards
- Consistent color-coding links inline highlights to confidence cards below

Weaknesses:
- Confidence-score-with-progress-bar visual device is common in AI trust marketing, limiting originality
- No motion evidence supplied so dynamic behavior (if any) can't be credited
- Layout is a standard left-text/right-mockup split without structural novelty

Why it does not reach the next tier: The section executes a familiar feature-card pattern cleanly with good internal hierarchy and content-fit, but neither the layout nor the visual device for 'confidence' is distinctive enough, and without motion evidence it cannot be credited for any dynamic interest that might elevate it.

## Adaptation guidance

- Effort: Medium
- Guidance: Rebuild the grid/card structure and highlight-to-citation mapping logic with placeholder copy and swap palette/fonts to match target brand; confidence-bar and toggle components are reusable but need new illustrative content.

What transfers:
- Two-column text/CTA plus mockup composition
- Nested card system showing citation detail with label, progress bar, and source link
- Color-coded highlight-to-card mapping concept

Dependencies:
- Specific example content (Tim Berners-Lee/CERN/1989 citations)
- Mono font for toggle/label elements
- Exact palette (orange accent, green confidence bar, light gray card background)

## Living vocabulary

- No reusable vocabulary candidates were supported by this section.

Only terms with status `active` enter the public taxonomy. Deferred and proposed terms remain available to later AI passes; rejected terms remain as provenance so they are not repeatedly reinvented.

## Provenance and limitations

- Section boundaries and naming: Gemini Pro visual observation
- Motion observations: Gemini Pro direct-video analysis
- Quality judgment: Claude
- Exact design facts: browser/CSS extraction at website scope
- Rubric: Design Details section rubric 3.2 (Typography 20%, Composition 20%, Motion 15%, Content 15%, Originality 15%, Adaptability 15%)
- No animation data provided, so motion axis is unscored
- Cannot verify exact font rendering or color values beyond supplied tokens
- Single static crop limits judgment of responsive or interactive behavior

## Usage guidance

Use this section as design evidence. Create an original implementation; do not reproduce the source copy, assets, or proprietary composition exactly.

## Build blueprint v3.2

### Purpose and classification

- Canonical type: features
- Source type: feature-card
- Structure: Left side text and button; right side UI mockup graphic.
- Layout: Left side text and button; right side UI mockup graphic.
- Styles: minimal, soft
- Components: heading, paragraph, button, ui mockup, data visualization
- Purpose: A feature card illustrating source citations and confidence scores within a text snippet.
- Visual signature: Text snippet with colorful highlight markers and progress bars underneath denoting confidence.
- Place on the page: 7 of 19, after Feature collection (`parallel-ai:C03`), before Feature collection (`parallel-ai:C04`)

### Crop and composition

- Crop: 1440×498px; aspect ratio 2.892:1
- Page bounds: 3464–3962px of 13235px
- Guidance: Preserve the documented hierarchy and relationships; exact measurements were not deterministically captured.

### Exact typography evidence

The sectionScale values were measured inside this crop. The siteRoles values explain how those faces function across the source website; they must not replace section measurements.

```json
{
  "sectionScale": [
    {
      "role": "UI/supporting text",
      "family": "ftSystemMono",
      "stack": "ftSystemMono, \"ftSystemMono Fallback\", ui-monospace, \"SF Mono\", Menlo, monospace",
      "size": "12px",
      "weight": "500",
      "lineHeight": "18px",
      "letterSpacing": "-0.2px",
      "sample": "HIGH CONFIDENCE",
      "element": "span",
      "occurrences": 4,
      "sourceId": "font-37"
    }
  ],
  "siteRoles": [
    {
      "role": "display",
      "size": "36px",
      "family": "gerstnerProgramm",
      "source": "computed",
      "traits": "Regular",
      "weight": "500",
      "evidence": "font-6: computed CSS at 1440×1000; AI role: gerstnerProgramm 36px, used for the main hero headline 'Where agents find answers'.",
      "sampleId": "font-6",
      "confidence": 0.9,
      "lineHeight": "40px",
      "letterSpacing": "normal"
    },
    {
      "role": "heading",
      "size": "32px",
      "family": "gerstnerProgramm",
      "source": "computed",
      "traits": "Regular",
      "weight": "500",
      "evidence": "font-4: computed CSS at 1440×1000; AI role: gerstnerProgramm 32px, used for major section headings like 'Put the web to work across every industry'.",
      "sampleId": "font-4",
      "confidence": 0.9,
      "lineHeight": "36px",
      "letterSpacing": "normal"
    },
    {
      "role": "body",
      "size": "16px",
      "family": "gerstnerProgramm",
      "source": "computed",
      "traits": "Regular",
      "weight": "500",
      "evidence": "font-11: computed CSS at 1440×1000; AI role: gerstnerProgramm 16px, used for descriptive paragraphs under features.",
      "sampleId": "font-11",
      "confidence": 0.85,
      "lineHeight": "24px",
      "letterSpacing": "0.2px"
    },
    {
      "role": "mono",
      "size": "13px",
      "family": "ftSystemMono",
      "source": "computed",
      "traits": "Regular",
      "weight": "400",
      "evidence": "font-9: computed CSS at 1440×1000; AI role: ftSystemMono 13px, used for navigation links, smaller metadata, and technical accents.",
      "sampleId": "font-9",
      "confidence": 0.95,
      "lineHeight": "16px",
      "letterSpacing": "0.2px"
    }
  ]
}
```

### Contextual design review

```json
{
  "status": "client-review-required",
  "checks": {
    "hierarchy": "Does each eyebrow, label and text level add useful information or clarify a necessary decision?",
    "decoration": "Do borders, effects, motion and spacing explain grouping or express a specific idea?",
    "repetition": "Can repeated claims, descriptions or actions be removed without losing needed information?",
    "identity": "What visible relationship between this offer, actual copy, imagery, typography and space gives the composition a convincing identity? Name its contribution and losses; matching ingredients or sparse styling are insufficient.",
    "reference": "Does it retain the source's dominant explanatory effect, media role, type balance and quiet space, not just columns?"
  },
  "heroMedia": {
    "appliesWhen": "A hero relies on focal media. A reasoned no-image hero remains valid and is judged by its visible composition.",
    "plan": "Record the image/headline first impression, actual available asset and crop, source image contribution, replacement contribution and losses before studies.",
    "review": "Does the actual hero suggest an offer, audience and experience appropriate to the whole brief? Quiet copy space or a recognizable subject is insufficient. One activity may lead without depicting all offers; justify its emphasis and resolve misleading implications. Missing assets or uncertain essential effects remain unverified."
  },
  "optionMedia": {
    "appliesWhen": "A section uses imagery to help visitors distinguish choices.",
    "planPerChoice": [
      "visitor distinction",
      "observable image evidence",
      "available asset or unresolved dependency",
      "crop retaining the distinguishing detail"
    ],
    "review": "Inspect the actual images. Shared atmosphere, changed crops or matching cards do not establish choice-specific meaning. If that role fails, resolve assets, choose an executable alternative or record lost/unverified and reject. Text comparison can be valid; it preserves a different contribution."
  },
  "noteCheck": "Check editorial interpretations against the received image; retain conflicts and unknown states instead of inventing selection or image meaning.",
  "decision": "Judge brief fit and positive character separately from layout preservation. Compare actual renders/references; essential lost or unverified effects prevent proceed. Reject either or both weak directions after inspection.",
  "qualityCertified": false
}
```

### Typography preservation review

```json
{
  "beforeStudy": "Use the actual reference image and captured section values to describe what its typography contributes: letter proportions and width, weight and contrast, case, line breaks and text-block shape, scale, spacing and relationship to the image. Label visual observations separately from captured facts and unknowns.",
  "substitution": "Choose an available, permitted face for the brief. Explain any substitute by the source relationships it preserves and any deliberate change; a familiar family, a serif/sans category or a mood label alone is not a justification. Do not copy an unavailable proprietary font or ban a common family merely because it is common.",
  "finalCheck": "Compare the actual rendered headline and supporting type beside this reference at the intended viewport. Check the loaded face/fallback and visible proportions, weight, line breaks, scale, spacing, contrast and image balance. Revise or reject when an essential typographic contribution is lost or unverified; a layout match or a font name is not a typography pass.",
  "unknowns": [
    "Glyph proportions, optical weight, actual line breaks, text-block shape and type-to-image balance require inspection of the reference image.",
    "Actual rendered face, font availability/licensing and responsive typography are not verified by this response."
  ]
}
```

### Exact color evidence

The section samples record where each computed value was used. Functional roles come from the website-level classifier and remain separate.

```json
{
  "sectionUsage": [
    {
      "value": "#68BD78",
      "cssValue": "rgb(104, 189, 120)",
      "alpha": 1,
      "appliedAs": [
        "background"
      ],
      "occurrences": 3,
      "sourceId": "color-40"
    }
  ],
  "functionalPalette": [
    {
      "hex": "#FFFFFF",
      "name": "canvas",
      "role": "canvas",
      "source": "computed",
      "evidence": "color-1: computed rgb(255, 255, 255); AI role: Pure white (#FFFFFF) used extensively as the main background color for most sections.",
      "sampleId": "color-1",
      "confidence": 0.95
    },
    {
      "hex": "#181818",
      "name": "text",
      "role": "text",
      "source": "computed",
      "evidence": "color-5: computed rgb(24, 24, 24); AI role: Dark gray/black (#181818) used for primary headings and body text.",
      "sampleId": "color-5",
      "confidence": 0.95
    },
    {
      "hex": "#FB631B",
      "name": "primary action",
      "role": "primary-action",
      "source": "computed",
      "evidence": "color-22: computed rgb(251, 99, 27); AI role: Bright orange (#FB631B) used for primary CTA buttons like 'Log in' and 'Start building for free'.",
      "sampleId": "color-22",
      "confidence": 0.95
    },
    {
      "hex": "#858483",
      "name": "muted text",
      "role": "muted-text",
      "source": "computed",
      "evidence": "color-3: computed rgb(133, 132, 131); AI role: Medium gray (#858483) used for secondary text like navigation links and descriptive subtext.",
      "sampleId": "color-3",
      "confidence": 0.9
    },
    {
      "hex": "#E5E5E5",
      "name": "border",
      "role": "border",
      "source": "computed",
      "evidence": "color-32: computed rgb(229, 229, 229); AI role: Light gray (#E5E5E5) used for borders around inputs, buttons, and structural lines.",
      "sampleId": "color-32",
      "confidence": 0.8
    },
    {
      "hex": "#E9F0F5",
      "name": "surface",
      "role": "surface",
      "source": "computed",
      "evidence": "color-24: computed rgb(233, 240, 245); AI role: Light blue/gray (#E9F0F5) used for background panels or blocks, such as the top announcement bar.",
      "sampleId": "color-24",
      "confidence": 0.7
    },
    {
      "hex": "#FF743D",
      "name": "accent",
      "role": "accent",
      "source": "computed",
      "evidence": "color-20: computed rgb(255, 116, 61); AI role: Another shade of orange (#FF743D) used in highlight blocks or accents.",
      "sampleId": "color-20",
      "confidence": 0.7
    }
  ]
}
```

### Design tokens

```json
{
  "radius": "Small border-radius (e.g., 2px-4px) on form elements and buttons, though largely imperceptible, presenting as sharp.",
  "density": "Low density; high amount of negative space around text blocks and between horizontal content bands.",
  "evidence": "Visual inspection of the screenshots shows wide margins, sharp-edged buttons ('Log in', 'API Playground'), solid color fills for primary buttons, and distinct 1px gray borders separating elements like the FAQ list.",
  "borderStyle": "Thin, 1px solid borders using light grays (color-32) for delineating sections, buttons, and UI mockups.",
  "buttonStyle": "Solid fill for primary actions with sharp corners; outlined with transparent backgrounds for secondary actions.",
  "cornerStyle": "Mostly square or very slightly rounded corners on elements like buttons and cards, leaning towards a sharp, technical look.",
  "contentWidth": "Constrained central column for text content (approx 800-1000px), with hero graphics and full-width background bands extending further.",
  "spacingRhythm": "Generous vertical spacing between major sections, creating a distinct, uncrowded layout. Grid layouts in features use moderate gaps."
}
```

### Reconstruction specification

This is the implementation contract for the captured desktop viewport. Prefer section-specific facts here over general website descriptions.

- Root: 1344×627px; grid; padding {"top":"80px","left":"24px","right":"24px","bottom":"80px"}; gap 48px; background rgba(0, 0, 0, 0); radius 0px.
- Observed gaps: 6, 8, 48px.
- Representative content widths: 1344, 502, 328, 290px.
- Layout containers: 1; cards/surfaces: 0; media elements: 1; browser animations: 0.

#### Container, grid, and spacing

```json
{
  "viewport": {
    "width": 1440,
    "captureBounds": {
      "top": 3464,
      "bottom": 3962,
      "pageHeight": 13235
    }
  },
  "container": {
    "size": "1344×627px",
    "position": "x 48px, y 3398px",
    "display": "grid",
    "positionMode": "static",
    "padding": {
      "top": "80px",
      "left": "24px",
      "right": "24px",
      "bottom": "80px"
    },
    "margin": {
      "top": "0px",
      "left": "0px",
      "right": "0px",
      "bottom": "0px"
    },
    "gap": "48px",
    "columns": "64px 64px 64px 64px 64px 64px 64px 64px 64px 64px 64px 64px",
    "background": "rgba(0, 0, 0, 0)",
    "radius": "0px",
    "border": "0px solid rgb(229, 229, 229)",
    "shadow": "none",
    "overflow": "clip visible"
  },
  "spacing": {
    "observedGapsPx": [
      6,
      8,
      48
    ],
    "representativeContentWidthsPx": [
      1344,
      502,
      328,
      290
    ]
  },
  "columns": [
    {
      "element": "section · Production-grade trustParallel's Web Agents use Basis to attach provenance and calibrated confidence",
      "size": "1344×627px",
      "position": "x 48px, y 3398px",
      "display": "grid",
      "template": "64px 64px 64px 64px 64px 64px 64px 64px 64px 64px 64px 64px",
      "direction": "row",
      "gap": "48px"
    }
  ]
}
```

#### Cards and surfaces

```json
{
  "cards": [],
  "surfaces": {
    "radii": [
      "4px",
      "2px"
    ],
    "borders": [
      "1px solid rgb(214, 214, 214)",
      "1px solid rgba(0, 0, 0, 0)"
    ],
    "shadows": []
  }
}
```

#### Media treatment

```json
[
  {
    "element": "svg · svg",
    "size": "11×11px",
    "position": "x 668px, y 3680px",
    "aspectRatio": 1,
    "objectFit": "fill",
    "objectPosition": "50% 50%",
    "radius": "0px",
    "overflow": "hidden",
    "source": "source not captured"
  }
]
```

#### Browser-exposed animation parameters

```json
[]
```

### Measured geometry, surfaces, media, and animation

These raw values come from the saved element map and computed styles. Empty arrays mean the fact was not captured; they are not permission to invent source values.

```json
{
  "root": {
    "id": "ld-1027",
    "gap": "48px",
    "tag": "section",
    "rect": {
      "x": 48,
      "y": 3398,
      "width": 1344,
      "height": 627
    },
    "role": null,
    "label": "Production-grade trustParallel's Web Agents use Basis to attach provenance and calibrated confidence",
    "border": "0px solid rgb(229, 229, 229)",
    "margin": {
      "top": "0px",
      "left": "0px",
      "right": "0px",
      "bottom": "0px"
    },
    "radius": "0px",
    "shadow": "none",
    "columns": "64px 64px 64px 64px 64px 64px 64px 64px 64px 64px 64px 64px",
    "display": "grid",
    "padding": {
      "top": "80px",
      "left": "24px",
      "right": "24px",
      "bottom": "80px"
    },
    "overflow": "clip visible",
    "position": "static",
    "background": "rgba(0, 0, 0, 0)"
  },
  "cards": [],
  "media": [
    {
      "id": "ld-1067",
      "tag": "svg",
      "rect": {
        "x": 668,
        "y": 3680,
        "width": 11,
        "height": 11
      },
      "role": null,
      "label": "svg",
      "media": null,
      "radius": "0px",
      "overflow": "hidden",
      "objectFit": "fill",
      "aspectRatio": 1,
      "objectPosition": "50% 50%"
    }
  ],
  "bounds": {
    "top": 3464,
    "bottom": 3962,
    "pageHeight": 13235
  },
  "schema": "little-details-section-measurements-v1",
  "source": "saved DOM/CSS element and animation maps",
  "columns": [
    {
      "id": "ld-1027",
      "gap": "48px",
      "tag": "section",
      "rect": {
        "x": 48,
        "y": 3398,
        "width": 1344,
        "height": 627
      },
      "role": null,
      "label": "Production-grade trustParallel's Web Agents use Basis to attach provenance and calibrated confidence",
      "columns": "64px 64px 64px 64px 64px 64px 64px 64px 64px 64px 64px 64px",
      "display": "grid",
      "direction": "row"
    }
  ],
  "spacing": {
    "gapsPx": [
      6,
      8,
      48
    ],
    "representativeContentWidthsPx": [
      1344,
      502,
      328,
      290
    ]
  },
  "coverage": {
    "cards": 0,
    "media": 1,
    "animations": 0,
    "elementsInSection": 119
  },
  "surfaces": {
    "radii": [
      "4px",
      "2px"
    ],
    "borders": [
      "1px solid rgb(214, 214, 214)",
      "1px solid rgba(0, 0, 0, 0)"
    ],
    "shadows": []
  },
  "animations": [],
  "capturedAt": "2026-10-08T01:59:46.460Z",
  "limitations": [
    "Values describe the captured desktop viewport and may change at other breakpoints.",
    "Transforms, sticky layers, and virtualized content can make the inferred section root approximate.",
    "Animations include browser-exposed Web Animations API state; CSS or script motion that was inactive at capture time may be absent."
  ],
  "viewportWidth": 1440
}
```

### Observed motion

No timestamped authored motion is attached. Use only restrained baseline transitions.

The browser animation records above are deterministic parameters captured from active browser animations. The timestamped observations describe what Gemini saw in the video. Treat them as complementary evidence. When either source is empty or they conflict, state the uncertainty instead of inventing timing or easing.

### Responsive contract

- Measured viewport: 1440px wide.
- Mobile/tablet values: not measured by this section evidence unless a separate capture is explicitly listed.
- Preserve hierarchy and sequence; collapse simultaneous columns only where needed, maintain media aspect ratios, and verify touch targets and text wrapping at target breakpoints.

### Structure versus visual skin

These categories describe evidence, not independent layers that can be swapped without changing the design. Study the complete reference system before adapting it.

- Preserve: content hierarchy, layout relationships, section rhythm, interaction purpose.
- Adapt: brand colors, font family, copy, imagery, icons, decorative details.
- Rule: These compatibility categories are coupled: fonts, color and imagery can carry the layout's design logic. Preserve or purposefully replace their contribution while creating original branding, copy, assets, and implementation details.

### Adaptation and dependencies

- Effort: medium
- What transfers: Two-column text/CTA plus mockup composition; Nested card system showing citation detail with label, progress bar, and source link; Color-coded highlight-to-card mapping concept
- Dependencies: Specific example content (Tim Berners-Lee/CERN/1989 citations); Mono font for toggle/label elements; Exact palette (orange accent, green confidence bar, light gray card background)
- Guidance: Rebuild the grid/card structure and highlight-to-citation mapping logic with placeholder copy and swap palette/fonts to match target brand; confidence-bar and toggle components are reusable but need new illustrative content.

### Evidence readiness

- Coverage: 7/7
- Can build: Yes
- Missing facts: timestamped authored motion
- Warning: Buildable with adaptations for these unsupported facts: timestamped authored motion.

### Agent implementation prompt

Create an original features section inspired by the design evidence titled “Trust feature card with source citations”.

Purpose: A feature card illustrating source citations and confidence scores within a text snippet.

Structure: Left side text and button; right side UI mockup graphic.. Source layout label: Left side text and button; right side UI mockup graphic.. Preserve the documented hierarchy and relationships; exact measurements were not deterministically captured.

Visual signature to preserve at the pattern level: Text snippet with colorful highlight markers and progress bars underneath denoting confidence.

Components: heading, paragraph, button, ui mockup, data visualization.

Style direction: minimal, soft.

Observed crop: 1440×498px (2.892:1). Treat this as evidence of composition, not a mandatory output size.

Typography evidence: {"role":"display","size":"36px","family":"gerstnerProgramm","source":"computed","traits":"Regular","weight":"500","evidence":"font-6: computed CSS at 1440×1000; AI role: gerstnerProgramm 36px, used for the main hero headline 'Where agents find answers'.","sampleId":"font-6","confidence":0.9,"lineHeight":"40px","letterSpacing":"normal"} {"role":"heading","size":"32px","family":"gerstnerProgramm","source":"computed","traits":"Regular","weight":"500","evidence":"font-4: computed CSS at 1440×1000; AI role: gerstnerProgramm 32px, used for major section headings like 'Put the web to work across every industry'.","sampleId":"font-4","confidence":0.9,"lineHeight":"36px","letterSpacing":"normal"} {"role":"body","size":"16px","family":"gerstnerProgramm","source":"computed","traits":"Regular","weight":"500","evidence":"font-11: computed CSS at 1440×1000; AI role: gerstnerProgramm 16px, used for descriptive paragraphs under features.","sampleId":"font-11","confidence":0.85,"lineHeight":"24px","letterSpacing":"0.2px"} {"role":"mono","size":"13px","family":"ftSystemMono","source":"computed","traits":"Regular","weight":"400","evidence":"font-9: computed CSS at 1440×1000; AI role: ftSystemMono 13px, used for navigation links, smaller metadata, and technical accents.","sampleId":"font-9","confidence":0.95,"lineHeight":"16px","letterSpacing":"0.2px"}

Color evidence: {"hex":"#FFFFFF","name":"canvas","role":"canvas","source":"computed","evidence":"color-1: computed rgb(255, 255, 255); AI role: Pure white (#FFFFFF) used extensively as the main background color for most sections.","sampleId":"color-1","confidence":0.95} {"hex":"#181818","name":"text","role":"text","source":"computed","evidence":"color-5: computed rgb(24, 24, 24); AI role: Dark gray/black (#181818) used for primary headings and body text.","sampleId":"color-5","confidence":0.95} {"hex":"#FB631B","name":"primary action","role":"primary-action","source":"computed","evidence":"color-22: computed rgb(251, 99, 27); AI role: Bright orange (#FB631B) used for primary CTA buttons like 'Log in' and 'Start building for free'.","sampleId":"color-22","confidence":0.95} {"hex":"#858483","name":"muted text","role":"muted-text","source":"computed","evidence":"color-3: computed rgb(133, 132, 131); AI role: Medium gray (#858483) used for secondary text like navigation links and descriptive subtext.","sampleId":"color-3","confidence":0.9} {"hex":"#E5E5E5","name":"border","role":"border","source":"computed","evidence":"color-32: computed rgb(229, 229, 229); AI role: Light gray (#E5E5E5) used for borders around inputs, buttons, and structural lines.","sampleId":"color-32","confidence":0.8} {"hex":"#E9F0F5","name":"surface","role":"surface","source":"computed","evidence":"color-24: computed rgb(233, 240, 245); AI role: Light blue/gray (#E9F0F5) used for background panels or blocks, such as the top announcement bar.","sampleId":"color-24","confidence":0.7} {"hex":"#FF743D","name":"accent","role":"accent","source":"computed","evidence":"color-20: computed rgb(255, 116, 61); AI role: Another shade of orange (#FF743D) used in highlight blocks or accents.","sampleId":"color-20","confidence":0.7}

Typography measured inside this section: {"id":"font-37","size":"12px","count":4,"family":"ftSystemMono","traits":"uppercase","weight":"500","contexts":[{"tag":"span","top":3677,"text":"HIGH CONFIDENCE","property":"font"},{"tag":"span","top":4324,"text":"4 TASKS","property":"font"},{"tag":"span","top":4404,"text":"4 TASKS","property":"font"}],"fontStack":"ftSystemMono, \"ftSystemMono Fallback\", ui-monospace, \"SF Mono\", Menlo, monospace","lineHeight":"18px","letterSpacing":"-0.2px"}

Colors measured inside this section: {"id":"color-40","hex":"#68BD78","alpha":1,"count":3,"contexts":[{"tag":"span","top":3782,"text":"","property":"background"}],"cssValue":"rgb(104, 189, 120)"}

Exact section measurements from the saved element map: root {"rect":{"x":48,"y":3398,"width":1344,"height":627},"padding":{"top":"80px","left":"24px","right":"24px","bottom":"80px"},"gap":"48px","columns":"64px 64px 64px 64px 64px 64px 64px 64px 64px 64px 64px 64px","overflow":"clip visible"}; spacing {"gapsPx":[6,8,48],"representativeContentWidthsPx":[1344,502,328,290]}; surfaces {"radii":["4px","2px"],"borders":["1px solid rgb(214, 214, 214)","1px solid rgba(0, 0, 0, 0)"],"shadows":[]}; media [{"tag":"svg","rect":{"x":668,"y":3680,"width":11,"height":11},"aspectRatio":1,"objectFit":"fill","objectPosition":"50% 50%","radius":"0px"}]

Do not invent signature motion. Use only restrained baseline transitions if the product needs them.

Transfer these principles: Two-column text/CTA plus mockup composition; Nested card system showing citation detail with label, progress bar, and source link; Color-coded highlight-to-card mapping concept.

Dependencies: Specific example content (Tim Berners-Lee/CERN/1989 citations); Mono font for toggle/label elements; Exact palette (orange accent, green confidence bar, light gray card background).

Adaptation guidance: Rebuild the grid/card structure and highlight-to-citation mapping logic with placeholder copy and swap palette/fonts to match target brand; confidence-bar and toggle components are reusable but need new illustrative content.

Study layout, typography, color, imagery and spacing as one coordinated source system. Record what creates its effect before producing a concept; preserve or purposefully replace each consequential relationship when adapting the business content and assets.

Use new copy, imagery, branding, and implementation details. Do not reproduce the source website or its proprietary assets.
