# Agent Brief. build in the style of opentag.build

> Machine-extracted from a live on-demand funnel teardown (2026-10-24). 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 |
|-----|------:|-------------|
| `#ffffff` | 56.5% | background |
| `#f4f5f7` | 14.1% | background |
| `#894b94` | 12.8% | support |
| `#eef0f3` | 9.2% | background |
| `#26251e` | 1.8% | support |
| `#6f3a82` | 1.1% | support |
| `#f5f5f4` | 0.7% | background |
| `#00cbb4` | 0.7% | accent/brand |

Curated roles: `accent=#894b94` · `bg=#ffffff` · `surface=#f4f5f7` · `text=#25282d`

## Type
- Display: `Manrope`
- Body: `Manrope`
- Size scale (px): 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 24, 38
- Radius (px): 5, 7, 10, 12, 50, 9999

## Patterns detected (fact-based). 4/11
- **Us-vs-them comparison**. A comparison table framing the brand against alternatives. _(home: The most configurable AI coworker. Feature comparison between openTag and hosted AI agents)_
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: FAQs Can I use my existing AI subscriptions with openTag? What do I need to use openTag? H)_
- **Trusted-by logo wall**. Customer/company logos or a "trusted by / used by" claim. _(home: used by)_
- **Demo / docs entry**. A "book a demo" or documentation / API entry point. _(home: Read the docs)_

## 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.