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

> Machine-extracted from a live on-demand funnel teardown (2026-10-16). 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 |
|-----|------:|-------------|
| `#ffffff` | 98.6% | background |
| `#2d6dc3` | 1.4% | accent/brand |

Curated roles: `primary=#2d6dc3` · `accent=#2d6dc3` · `bg=#ffffff` · `surface=#ffffff` · `text=#4f5a6d`

## Type
- Display: `Instrument Serif`
- Body: `Inter`
- Size scale (px): 10, 12, 14, 16, 18, 20, 22, 30, 48, 60
- Radius (px): 0, 6, 10, 12, 16, 33554400

## Patterns detected (fact-based). 1/11
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: What is a video to prompt generator? It turns any video into a text prompt that recreates )_

## 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.