# Agent Brief. build in the style of tarot.bitio.ai

> Machine-extracted from a live on-demand funnel teardown (2026-10-02). 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 |
|-----|------:|-------------|
| `#101314` | 41.8% | support |
| `#07101d` | 24% | support |
| `#18201c` | 18.1% | support |
| `#252c29` | 7.2% | support |
| `#191e1d` | 2.9% | support |
| `#b99a61` | 2.3% | support |
| `#020308` | 2.2% | support |
| `#8bbcff` | 1.3% | accent/brand |

Curated roles: `primary=#8bbcff` · `accent=#8bbcff` · `bg=#101314` · `surface=#101314` · `text=#f0ebdf`

## Type
- Display: `Cormorant Garamond`
- Body: `Inter`
- Size scale (px): 9, 10, 11, 12, 13, 14, 16, 18, 21, 23, 27, 60
- Radius (px): 3, 4, 6, 8, 50

## Patterns detected (fact-based). 2/11
- **Us-vs-them comparison**. A comparison table framing the brand against alternatives. _(home: comparison table: )_
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: COMMON QUESTIONS Tarot reading FAQ How does an online tarot reading work? Write a little a)_

## 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.
