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

> Machine-extracted from a live on-demand funnel teardown (2026-10-13). 100% facts —
> measured tokens, detected patterns, harvested proof strings. No LLM interpretation.
> Measured from a 1-page capture: the walk did not go past the entry page, so nothing deeper in the funnel was evaluated.
> Tokens: `tokens.json` / `tailwind.css`.

**Funnel:** Homepage / Lander

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#141412` | 64.8% | support |
| `#191916` | 33.1% | support |
| `#7fb491` | 1.9% | support |
| `#e8654f` | 0.1% | accent/brand |
| `#34332e` | 0.1% | support |

Curated roles: `accent=#7fb491` · `bg=#141412` · `surface=#141412` · `text=#9a938c`

## Type
- Display: `DM Sans`
- Body: `DM Sans`
- Size scale (px): 11, 12, 13, 14, 15, 16, 17, 19, 20, 21, 38, 60
- Radius (px): 2, 6, 10, 12, 16, 50

## Patterns detected (fact-based). 1/15
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: So how does this actually work? + You bring in any material in the language you are learni)_

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

## Funnel facts
- Depth reached: 1 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 1-page capture: the walk did not go past the entry page, so nothing deeper in the funnel was evaluated.