# Agent Brief. build in the style of yylo.dev

> Machine-extracted from a live on-demand funnel teardown (2026-09-01). 100% facts —
> measured tokens, detected patterns, harvested proof strings. No LLM interpretation.
> Measured from a 3-step funnel walk.
> Tokens: `tokens.json` / `tailwind.css`.

**Funnel:** Homepage / Lander → Compare → Yylo Vs Cursor

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#fcfbf7` | 45% | background |
| `#171a21` | 29.8% | support |
| `#05090f` | 20.1% | support |
| `#11141b` | 4.8% | support |
| `#174eb6` | 0.2% | accent/brand |

Curated roles: `accent=#171a21` · `bg=#fcfbf7` · `surface=#fcfbf7` · `text=#424955`

## Type
- Display: `Arial`
- Body: `SFMono-Regular`
- Size scale (px): 11, 12, 13, 14, 16, 21, 26, 65, 101
- Radius (px): 4, 9, 10, 999

## Patterns detected (fact-based). 2/11
- **Us-vs-them comparison**. A comparison table framing the brand against alternatives. _(p3: comparison table: Shared job · YYLO · Cursor · Evidence verdict)_
- **Demo / docs entry**. A "book a demo" or documentation / API entry point. _(home: docs link; p2: documentation; p3: documentation)_

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

## Funnel facts
- Depth reached: 3 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 3-step funnel walk.