# Agent Brief. build in the style of hotellobby-ai.net

> Machine-extracted from a live on-demand funnel teardown (2026-10-06). 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 → Pricing

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#000000` | 83% | support |
| `#f4f4f6` | 13.1% | background |
| `#ffffff` | 3.9% | background |

Curated roles: `accent=#f4f4f6` · `bg=#f4f4f6` · `surface=#ffffff` · `text=#a5a5af`

## Type
- Display: `Inter Tight Variable`
- Body: `Inter Variable`
- Size scale (px): 10, 11, 12, 13, 14, 15, 16, 17, 20, 30, 36, 56
- Radius (px): 4, 6, 8, 12, 33554400

## Patterns detected (fact-based). 2/15
- **Us-vs-them comparison**. A comparison table framing the brand against alternatives. _(home: comparison grid: 6 rows)_
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: What is Hotel Lobby AI? Hotel Lobby AI creates duet videos from two reference photos using)_

## 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.