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

> Machine-extracted from a live on-demand funnel teardown (2026-08-15). 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 |
|-----|------:|-------------|
| `#0a0a0e` | 61.3% | support |
| `#0a0a0f` | 15.4% | support |
| `#ffffff` | 8.8% | background |
| `#121826` | 7.5% | support |
| `#7b5cff` | 3.4% | accent/brand |
| `#111118` | 2.9% | support |
| `#0a0a0d` | 0.4% | support |
| `#00e5ff` | 0.2% | accent/brand |

Curated roles: `primary=#7b5cff` · `accent=#7b5cff` · `bg=#ffffff` · `surface=#ffffff` · `text=#ffffff`

## Type
- Display: `Space Grotesk`
- Body: `Inter`
- Size scale (px): 11, 12, 13, 14, 15, 16, 17, 18, 20, 24, 26, 44
- Radius (px): 10, 12, 16, 24, 50, 100

## Patterns detected (fact-based). 2/5
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: How do businesses show up in ChatGPT? By being structured, trusted, and aligned with real )_
- **Press / "as seen in"**. Media logos or an "as seen in / featured in" claim borrowing publication credibility. _(home: AS SEEN ON
Clutch & Manifest
Crunchbase
G2 Software Ratings
TrustPilot)_

## Proof language (harvested strings → templates)
- `AS SEEN ON Clutch & Manifest Crunchbase G2 Software Ratings TrustPilot`. e.g. "AS SEEN ON Clutch & Manifest Crunchbase G2 Software Ratings TrustPilot"

## Funnel facts
- Depth reached: 1 step(s)
- Proof points: 1 across 1 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 1-page capture: the walk did not go past the entry page, so nothing deeper in the funnel was evaluated.