# Agent Brief. build in the style of researchmaster.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 → En

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#f8f7f2` | 47.2% | background |
| `#f3f2ec` | 46.4% | background |
| `#ffffff` | 4.6% | background |
| `#fbfaf5` | 1.5% | background |
| `#151613` | 0.2% | support |
| `#b9f24a` | 0.1% | accent/brand |
| `#eeede6` | 0% | background |
| `#edf1da` | 0% | background |

Curated roles: `primary=#f3f2ec` · `accent=#f3f2ec` · `bg=#f8f7f2` · `surface=#f3f2ec` · `text=#686a61`

## Type
- Display: `ui-sans-serif`
- Body: `ui-sans-serif`
- Size scale (px): 6, 10, 11, 12, 14, 15, 16, 18, 48, 62
- Radius (px): 5, 6, 7, 8, 12, 14

## Patterns detected (fact-based). 5/11
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: FAQ Questions before you start. Clear answers before you start your next research workflow)_
- **Free trial / freemium**. A free trial, free tier, or "no credit card" entry offer. _(home: Get Started Free)_
- **Trusted-by logo wall**. Customer/company logos or a "trusted by / used by" claim. _(home: logo wall (15 distinct marks))_
- **Usage / adoption proof**. A count of developers / teams / companies / stars using the product. _(home: 158 billion of pet spending in 2024 and projects)_
- **Pricing tiers**. Named plan tiers with per-month / per-seat pricing. _(home: free, $19/mo)_

## Proof language (harvested strings → templates)
- `Free delivery`. e.g. "Free delivery"

## Funnel facts
- Depth reached: 1 step(s)
- Proof points: 1 across 1 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.