# Agent Brief. build in the style of app.valueize.com

> Machine-extracted from a live on-demand funnel teardown (2026-08-09). 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

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#f5f5f5` | 67.8% | background |
| `#ffffff` | 31.1% | background |
| `#99b6ff` | 1.1% | accent/brand |

Curated roles: `primary=#99b6ff` · `accent=#99b6ff` · `bg=#f5f5f5` · `surface=#ffffff` · `text=#7d7d7d`

## Type
- Display: `DM Sans`
- Body: `DM Sans`
- Size scale (px): 14, 18, 36
- Radius (px): 4, 6, 8

## Patterns detected (fact-based). 0/5
- _(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.