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

> Machine-extracted from a live on-demand funnel teardown (2026-08-18). 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 |
|-----|------:|-------------|
| `#000065` | 57.7% | accent/brand |
| `#ffffff` | 41.7% | background |
| `#f5f5f5` | 0.4% | background |
| `#ffc000` | 0.2% | accent/brand |

Curated roles: `primary=#000065` · `accent=#000065` · `bg=#ffffff` · `surface=#f5f5f5` · `text=#000065`

## Type
- Display: `poppins`
- Body: `poppins`
- Size scale (px): 10, 11, 12, 13, 14, 15, 16, 18, 20, 24, 30, 48
- Radius (px): 4, 10, 14, 16, 24, 33554400

## Patterns detected (fact-based). 1/5
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: How does TicketWhiz work? +)_

## 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.