# Agent Brief. build in the style of ai-attractivenesstest.com

> Machine-extracted from a live on-demand funnel teardown (2026-08-03). 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 |
|-----|------:|-------------|
| `#24222d` | 67.4% | support |
| `#000000` | 32.6% | support |

Curated roles: `primary=#24222d` · `accent=#24222d` · `bg=#24222d` · `surface=#24222d` · `text=#ffffff`

## Type
- Display: `Geist`
- Body: `Geist`
- Size scale (px): 14, 16, 18, 20, 24, 36, 48
- Radius (px): 4, 6, 8, 10, 14, 16

## Patterns detected (fact-based). 2/5
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: How accurate is the AI attractiveness test? ▼)_
- **Press / "as seen in"**. Media logos or an "as seen in / featured in" claim borrowing publication credibility. _(home: featured on)_

## Proof language (harvested strings → templates)
- `{X} out of 5`. e.g. "4.8 out of 5"

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

## 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.