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

> Machine-extracted from a live on-demand funnel teardown (2026-08-03). 100% facts —
> measured tokens, detected patterns, harvested proof strings. No LLM interpretation.
> Measured from a 4-step funnel walk.
> Tokens: `tokens.json` / `tailwind.css`.

**Funnel:** Homepage / Lander → Pricing → Page → Auth

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#ffffff` | 35.8% | background |
| `#030303` | 21.2% | support |
| `#050505` | 17.1% | support |
| `#0b0b0d` | 11.1% | support |
| `#000000` | 5.9% | support |
| `#06070a` | 4.2% | support |
| `#111216` | 1.7% | support |
| `#101116` | 1.5% | support |

Curated roles: `primary=#06070a` · `accent=#06070a` · `bg=#ffffff` · `surface=#ffffff` · `text=#ffffff`

## Type
- Display: `Inter`
- Body: `Inter`
- Size scale (px): 10, 11, 12, 13, 14, 15, 16, 18, 20, 36, 40, 48
- Radius (px): 4, 5, 6, 10, 12, 9999

## Patterns detected (fact-based). 2/15
- **Anchor / strikethrough pricing**. A struck-through original price or an "X% off" claim. _(home: $0.1345 / $0.1614 / $0.3034 / $0.3628 / $0.6820 / $0.8184 / Save 47%; p3: $0.1345 / $0.1614 / $0.3034 / $0.3628 / $0.6820 / $0.8184 / Save 47%)_
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: FAQ; p3: FAQ)_

## Proof language (harvested strings → templates)
- `Save {N}%`. e.g. "Save 47%"

## Funnel facts
- Depth reached: 4 step(s)
- Proof points: 1 across 2 step(s)
- Discount/anchor pricing: yes · Countdown: no · Subscription: no

## To replicate
Match the palette + type tokens above and deploy the detected patterns. Measured from a 4-step funnel walk.