# Agent Brief. build in the style of bulkpictools.com

> 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 |
|-----|------:|-------------|
| `#f8fafc` | 64.4% | background |
| `#ffffff` | 16.5% | background |
| `#3b82f6` | 14.9% | accent/brand |
| `#f1f5f9` | 1.3% | background |
| `#eff6ff` | 0.7% | background |
| `#94a3b8` | 0.6% | support |
| `#faf5ff` | 0.4% | background |
| `#fffbeb` | 0.3% | background |

Curated roles: `primary=#3b82f6` · `accent=#3b82f6` · `bg=#f8fafc` · `surface=#ffffff` · `text=#94a3b8`

## Type
- Display: `Inter`
- Body: `Inter`
- Size scale (px): 8, 10, 11, 12, 14, 16, 18, 20, 24, 30, 36, 60
- Radius (px): 6, 8, 12, 16, 20, 9999

## Patterns detected (fact-based). 5/11
- **Us-vs-them comparison**. A comparison table framing the brand against alternatives. _(home: comparison table: FEATURE · BULKPICTOOLS · CLOUD COMPRESSION TOOLS · SINGLE-IMAGE EDITORS )_
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: Frequently Asked Questions)_
- **Free trial / freemium**. A free trial, free tier, or "no credit card" entry offer. _(home: Free forever)_
- **Trusted-by logo wall**. Customer/company logos or a "trusted by / used by" claim. _(home: logos: yo.directory, LaunchClash, Submit AI Tools)_
- **Usage / adoption proof**. A count of developers / teams / companies / stars using the product. _(home: 1,000,000+ Users)_

## 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: 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.