# Agent Brief. build in the style of systima.ai

> Machine-extracted from a live on-demand funnel teardown (2026-07-14). 100% facts —
> measured tokens, detected patterns, harvested proof strings. No LLM interpretation.
> Single-page capture (MVP): homepage/landing page only, no funnel walk.
> Tokens: `tokens.json` / `tailwind.css`.

**Category (label):** —
**Funnel:** Homepage / Lander → Solutions

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#1a1d1f` | 39.6% | support |
| `#ffffff` | 30.5% | background |
| `#f5f4f0` | 29.5% | background |
| `#3d6b5e` | 0.3% | support |
| `#8b5c3e` | 0% | support |
| `#eceae5` | 0% | background |
| `#4a8272` | 0% | support |

Curated roles: `primary=#1a1d1f` · `accent=#1a1d1f` · `bg=#ffffff` · `surface=#f5f4f0` · `text=#ffffff`

## Type
- Display: `Fraunces`
- Body: `Outfit`
- Size scale (px): 10, 11, 12, 13, 14, 15, 17, 19, 21, 32, 40, 44
- Radius (px): 4, 6, 8, 10, 12, 50

## Patterns detected (fact-based). 1/8
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(p2: Frequently asked questions How do you handle hallucination risk in legal AI? + Every legal)_

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

## Funnel facts
- Depth reached: 2 step(s) (single-page MVP capture)
- 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. This is a single-page capture. no cart/checkout tactics were evaluated.