Confidential

Armadello
The Next Generation

AI-powered e-commerce analytics for every brand,
not just those who can afford a data analyst.

February 2026

The Opportunity

Most E-Commerce Brands
Are Flying Blind

Enterprise brands have data teams. Everyone else has spreadsheets and gut feel.

📊 The Data Gap

Shopify's built-in reports are disconnected. Critical insights require combining multiple reports manually. Hours of work for basic answers.

💷 The Cost Gap

Hiring a data analyst: £35-50k/year. Analytics platforms with AI: $399+/month. Most brands under £500k revenue can't justify either.

🤖 The AI Gap

AI analytics tools exist — but they're locked behind enterprise tiers. The businesses that would benefit most from automated insights can't access them.

"All your e-commerce data in one place — actionable insights, attribution you can trust, growth you can measure." — The Armadello vision. We're delivering it.
The Solution

AI Analytics
For Every Brand

A data analyst in every dashboard. Automated insights daily. Interactive AI when you need deeper answers. Starting from day one, on every tier.

Day 1
AI insights from first login
3
AI specialist modes
24mo
Historical data synced
Minutes
To onboard a new brand

🌅 Daily Automated Insights

Every morning, AI analyses each client's data overnight and surfaces what matters: anomalies, trends, opportunities. No tokens used — it's part of the platform. Every tier gets this.

💬 Interactive AI (Token-Based)

Need a deeper answer? Ask Lucia. "Why did AOV drop last week?" "Which campaign is cannibalising organic?" Tokens scale by tier, with top-ups available anytime.

Visualisations

The Dashboard

Interactive, real-time, and designed to answer questions at a glance.

Total Revenue
£33,847
↑ 12.4% vs last month
Average Order Value
£87.09
↑ 6.9% vs last month
Customer LTV
£142.30
↑ 3.2% vs last quarter
Conversion Rate
3.8%
↓ 0.3% vs last month

📈 Interactive Charts

Recharts-powered visualisations with hover tooltips, zoom, drill-down. Previous period shown as dotted overlays on area charts, ghost bars on bar charts.

🔄 Real-Time Sync

Shopify data syncs through BullMQ job queues into Supabase. Live updates, not daily CSV imports. Multiple refreshes per day.

📱 Fully Responsive

Works on desktop, tablet, and mobile. Tailwind + shadcn/ui component library — consistent, polished, fast.

Deep Dive

Reports That Tell Stories

Not just charts — structured reports that answer real business questions.

🔀 Attribution Flow (Sankey)

See the complete customer journey: first touch → intermediate steps → conversion. Which channels start journeys? Which close them? Where do people drop off?

Facebook Ads
Google Organic
Email (Klaviyo)
Direct
Product Page
Category Browse
Blog Content
💰 Purchase
✗ Abandoned

🗓️ Retention Cohorts (Heatmap)

Track customer groups over time. Which acquisition month produces the most loyal buyers? Where does retention drop off?

Month 1
Month 2
Month 3
Month 4
Month 5
Month 6
Sep '25
100%
42%
28%
21%
18%
14%
Oct '25
100%
46%
32%
24%
19%
Nov '25
100%
38%
25%
19%
Dec '25
100%
51%
33%

December cohort showing strongest retention — BFCM buyers coming back.

📉 Revenue Forecast

Predictive models with confidence bands. See where revenue is heading — not just where it's been.

🔁 Conversion Funnel

Visit → Add to Cart → Checkout → Purchase. See exactly where customers drop off and by how much.

📊 Sales Trends

702 lines of interactive charting. Area charts with dotted previous-period overlays. Bar charts with ghost comparisons.

AI Engine

Lucia — Your AI Data Team

Three domain experts that analyse data and give structured, actionable output. Not a chatbot — a thinking engine.

🏪 Commerce Expert

Thinks like a fractional CFO

  • Contribution margin analysis
  • Inventory turn optimisation
  • Cohort-level revenue forensics
  • Pricing elasticity signals
  • Cash flow impact modelling

📈 Growth Strategist

Thinks like a performance marketing director

  • Marginal ROAS analysis
  • Attribution path forensics
  • Channel saturation detection
  • Creative fatigue alerts
  • Budget reallocation modelling

🔬 Data Scientist

Thinks like a causal analyst

  • Statistical process control
  • Anomaly detection & alerts
  • Predictive demand modelling
  • Customer behaviour clustering
  • Seasonal trend analysis

Structured Output

→ HEADLINE  /  EVIDENCE  /  CONTEXT  /  ACTION

Every response: a clear headline insight, supporting evidence from the data, business context, and a specific next action. No waffle. No ambiguity.

AI For Everyone

AI Shouldn't Be a Luxury

The brands that need AI most — the ones without data teams — should get it first. Not last.

Every Tier Gets AI

Starter Daily insights + 50 prompts/mo
Pro Daily insights + 200 prompts/mo
Enterprise Daily insights + 1,000 prompts/mo
Any tier + Buy more tokens anytime

How It Works

Daily Insights (Free)

AI runs overnight analysis for every client. Surfaces anomalies, opportunities, and trends. Delivered to their dashboard each morning. Zero cost to the user — it's the product.

Interactive Prompts (Tokens)

"Why did our AOV drop this week?" "Which campaign drives the highest LTV customers?" Deeper questions use tokens from their allowance.

The Economics

AI models get cheaper every quarter. Today: ~£7/month for daily insights across 10 clients. Tomorrow: half that. Margins improve automatically.

This is the mass market play. A £29/month brand gets the same AI as a £399/month enterprise — just with fewer interactive prompts. The insights that matter come automatically.
Architecture

Real-Time Data Pipeline

From Shopify webhook to dashboard widget in seconds. Not daily CSV imports — live data.

The Pipeline

Shopify Event

Order placed, product updated, customer created

Webhook → BullMQ

Event hits our API → queued for processing

Worker Processing

Data cleaned, normalised, enriched with UTM data

Supabase (PostgreSQL)

Stored with org_id, RLS-protected, indexed

Dashboard Update

Client sees new data on next page load

Multi-Tenant by Design

One database, unlimited brands. Every row tagged with organization_id. Row Level Security means Company A physically cannot query Company B's data.

  • Single Supabase project: $25/month
  • Supports 100,000 monthly active users
  • 8GB storage included (plenty for text data)
  • Role system: owner / admin / member / viewer
  • Org switching for agencies & consultants
  • Superadmin panel for platform management

Onboarding a New Brand

Create org → OAuth connect Shopify → BullMQ pulls 24 months history → Lucia auto-configures → Client gets invite link.

Total time: minutes, not days.

Unit Economics

The Numbers

10 companies, 30 users. What it costs to run.

$25
Supabase Pro
~$20
Railway hosting
~$75
AI API (Sonnet)
~$8
Redis queues
~$128
Total monthly (10 companies)

~$13 per company

~$4.30 per user

Scaling

Going from 10 to 50 companies adds minimal cost. Supabase stays at $25. Railway adds ~$15. AI scales linearly but gets cheaper every quarter.

50 companies ≈ $250/month

$5 per company

Revenue Potential

At $29/company (matching current Essential pricing):

10 companies: $290 revenue / $128 cost

50 companies: $1,450 revenue / $250 cost

100 companies: $2,900 revenue / $400 cost

Profitable from client #5.

AI API costs based on Claude Sonnet. Costs decrease as models improve — Sonnet 4.7 expected to deliver Opus-level quality at Sonnet pricing.

Today

What's Ready Now

Built, tested, deployed. Working software — not wireframes or roadmap items.

✅ Dashboard

  • CLV widget with trend sparklines
  • Conversion funnel visualisation
  • Attribution summary cards
  • Quick actions panel
  • Recent orders with drill-down
  • Previous period overlays
  • Responsive on all devices

✅ Reports

  • Marketing attribution + Sankey flow
  • Revenue forecast with confidence
  • Customer retention cohort heatmap
  • Sales trends (interactive, 702 lines)
  • Pivot tables & comparison charts
  • Touchpoint detail panels

✅ Lucia AI

  • 3 specialist modes
  • Auto-skill selection engine
  • Structured HEADLINE → ACTION output
  • Server-only prompts (secure)
  • Interactive explorer chat
  • Prompt architecture ready for daily insights

✅ Platform

  • 48 protected pages
  • Invite-only authentication
  • Organisation management
  • Role-based access control
  • Guided onboarding flow
  • Settings & preferences
  • In-app changelog

✅ Infrastructure

  • Next.js 16 + TypeScript strict
  • Supabase PostgreSQL + RLS
  • BullMQ + Redis job queues
  • Railway auto-deploy from git
  • CI/CD security scanning
  • Shopify REST API v2024-01

✅ Security

  • Full penetration test — passed
  • CSP + HSTS + full header suite
  • XSS protection + input sanitisation
  • AI prompts server-only (never bundled)
  • Bundle scanning on every push
  • Row Level Security per organisation
Tomorrow

What Can Be Ready Tomorrow

The architecture is in place. These aren't rebuilds — they're wiring jobs.

→ Days, Not Months

The queue infrastructure (BullMQ + Redis) means adding a new data source is a pipeline task, not an architecture change. Each integration is a worker that feeds into the same schema.

→ Weeks

Facebook/Meta Ads Integration

Campaign performance → attribution pipeline. Meta Marketing API, read access.

Google Ads Integration

Search + Shopping campaign data → unified attribution.

Stripe Billing

Self-serve signup → plan selection → payment → auto-provisioned org. Schema already has Stripe fields.

White-Label Theming

Per-org branding: logo, colours, custom domain. Architecture supports it — needs UI.

→ On the Horizon

  • WooCommerce support
  • Magento support
  • Amazon Seller Central
  • Klaviyo email attribution
  • TikTok Ads
  • Google Search Console

The Vision Was Right.

The Tech Is Ready.

AI-powered e-commerce analytics that works for a £29/month brand as well as a £399/month enterprise. Real-time data. Interactive visualisations. Three AI specialists from day one.

$128
Monthly cost / 10 brands
3
AI specialists, every tier
48
Pages built & deployed
0
Reasons to wait

Everything in this presentation is deployed and running. Not planned. Not wireframed. Built.

1 / 12