# Agent Brief — build in the style of modal.com

> Machine-extracted from a live funnel teardown (2026-07-09). 100% facts — measured
> tokens, detected patterns, harvested proof strings. No LLM interpretation.
> Tokens: `tokens.json` / `tailwind.css`.

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

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#000000` | 50% | support |
| `#def0dd` | 32.1% | background |
| `#181818` | 16.6% | support |
| `#212525` | 0.8% | support |
| `#7fee64` | 0.3% | accent/brand |
| `#91c8ef` | 0.1% | support |
| `#07b976` | 0% | accent/brand |
| `#ff8de6` | 0% | accent/brand |

Curated roles: `primary=#def0dd` · `accent=#def0dd` · `bg=#def0dd` · `surface=#def0dd` · `text=#ddffdc`

## Type
- Display: `Goga`
- Body: `Inter Variable`
- Size scale (px): 12, 14, 16, 20, 21, 24, 28, 30, 36, 40, 42, 54
- Radius (px): 4, 8, 11, 12, 19, 25

## Patterns detected (fact-based) — 6/9
- **Us-vs-them comparison** — A comparison table framing the brand against alternatives. _(p2: comparison table)_
- **FAQ / objection handling** — An accordion / FAQ block answering objections. _(p2: FAQ/accordion)_
- **Trusted-by logo wall** — Customer/company logos or a "trusted by / used by" claim. _(home: trusted-by / logo cloud)_
- **Usage / adoption proof** — A count of developers / teams / companies / stars using the product. _(home: usage/adoption count)_
- **Pricing tiers** — Named plan tiers with per-month / per-seat pricing. _(home: pricing tiers; p2: pricing tiers)_
- **Demo / docs entry** — A "book a demo" or documentation / API entry point. _(home: demo / docs; p2: demo / docs)_

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

## Funnel facts
- Depth reached: 3 steps
- Proof points: 0 across 0 steps
- Free-gift line items (max on a step): 0
- Discount/anchor pricing: no · Countdown: no · Subscription: no
- Price continuity lander→checkout: not detected

## To replicate
Match the palette + type tokens above, deploy the detected patterns at the same funnel positions, and reuse the proof-language templates with your own numbers.