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

> Machine-extracted from a live on-demand funnel teardown (2026-09-16). 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 → Accounts

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#eef2f1` | 62.9% | background |
| `#ffffff` | 35.4% | background |
| `#0d9488` | 1.1% | accent/brand |
| `#fbfdfd` | 0.4% | background |
| `#fff7ed` | 0.1% | background |

Curated roles: `primary=#0d9488` · `accent=#0d9488` · `bg=#eef2f1` · `surface=#ffffff` · `text=#5b7180`

## Type
- Display: `Bricolage Grotesque`
- Body: `Roboto`
- Size scale (px): 11, 12, 14, 15, 16, 18, 20, 24, 30, 48
- Radius (px): 4, 6, 9, 12, 14, 16

## Patterns detected (fact-based). 1/7
- **Us-vs-them comparison**. A comparison table framing the brand against alternatives. _(home: comparison grid: 3 rows)_

## 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: no

## To replicate
Match the palette + type tokens above and deploy the detected patterns. Measured from a 2-step funnel walk.