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

> Machine-extracted from a live on-demand funnel teardown (2026-09-28). 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 → Pricing

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#f7f2eb` | 40.9% | background |
| `#1a1721` | 36.2% | support |
| `#ffffff` | 9.3% | background |
| `#16121f` | 6.6% | support |
| `#f2ebe1` | 6.6% | background |
| `#c46617` | 0.4% | accent/brand |

Curated roles: `accent=#f2ebe1` · `bg=#f7f2eb` · `surface=#ffffff` · `text=#575161`

## Type
- Display: `Playfair Display`
- Body: `Lora`
- Size scale (px): 11, 12, 13, 14, 16, 17, 19, 20, 25, 31, 61
- Radius (px): 4, 8, 12, 14, 16, 9999

## Patterns detected (fact-based). 2/15
- **Us-vs-them comparison**. A comparison table framing the brand against alternatives. _(p2: comparison table: Dimension · ichingonline.net · castiching.com · aiching.app · The Hexagr)_
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: Frequently Asked Questions; p2: Is this comparison unbiased? Not completely, and we disclose it up front: we operate The H; pricing: Can I buy a single reading and nothing else? What if my question changes after I pay? Can )_

## 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: yes

## To replicate
Match the palette + type tokens above and deploy the detected patterns. Measured from a 3-step funnel walk.
