# Agent Brief. build in the style of placementpapers.app

> Machine-extracted from a live on-demand funnel teardown (2026-08-13). 100% facts —
> measured tokens, detected patterns, harvested proof strings. No LLM interpretation.
> Measured from a 2-step funnel walk.
> Tokens: `tokens.json` / `tailwind.css`.

**Funnel:** Homepage / Lander → Product Vs Service Companies

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#ffffff` | 89.4% | background |
| `#f8f9fa` | 8.8% | background |
| `#e8f0fe` | 1.8% | background |

Curated roles: `primary=#e8f0fe` · `accent=#e8f0fe` · `bg=#ffffff` · `surface=#f8f9fa` · `text=#111111`

## Type
- Display: `Outfit`
- Body: `Outfit`
- Size scale (px): 12, 13, 14, 16, 18, 22, 34
- Radius (px): 2, 4, 6, 8, 50

## Patterns detected (fact-based). 1/5
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: Are placement papers free to access?; p2: Is it okay to join a service company if I couldn’t get into product?)_

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

## Funnel facts
- Depth reached: 2 step(s)
- Proof points: 0 across 0 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 2-step funnel walk.