# Agent Brief. build in the style of bestbuy.com

> Machine-extracted from a live on-demand funnel teardown (2026-08-10). 100% facts —
> measured tokens, detected patterns, harvested proof strings. No LLM interpretation.
> Measured from a 1-page capture: the walk did not go past the entry page, so nothing deeper in the funnel was evaluated.
> Tokens: `tokens.json` / `tailwind.css`.

**Funnel:** Homepage / Lander → Site → Cart

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#f3f4f6` | 44.6% | background |
| `#ffffff` | 34.5% | background |
| `#e4e5e8` | 18.8% | background |
| `#0046be` | 2% | accent/brand |
| `#f1f8ff` | 0% | background |

Curated roles: `primary=#0046be` · `accent=#0046be` · `bg=#f3f4f6` · `surface=#ffffff` · `text=#030303`

## Type
- Display: `-`
- Body: `Human BBY Digital`
- Size scale (px): 10, 12, 13, 14, 20, 28
- Radius (px): 4, 8, 16, 9999

## Patterns detected (fact-based). 0/15
- _(none detected)_

## Proof language (harvested strings → templates)
- _(none extracted)_

## Funnel facts
- Depth reached: 1 step(s)
- Proof points: 0 across 0 step(s)
- Discount/anchor pricing: no · Countdown: no · Subscription: no

## To replicate
Match the palette + type tokens above and deploy the detected patterns. Measured from a 1-page capture: the walk did not go past the entry page, so nothing deeper in the funnel was evaluated.