Five sources. One queryable rollup.
Cross-channel rollup with cohort retention, per-customer channel preference, send-time optimisation, and predictive LTV. Built on a multi-tenant data plane with per-shop schema isolation. Replace four Looker dashboards with one SQL surface.
Most analytics is a dashboard.
Reports answer 'what.' Operators need to know 'who, when, and what next.'
Five tabs, one cohort.
GA4 in one tab, Shopify in another, Google Ads in a third, Looker on top. Reconciling channels is manual. The cohort never converges.
Send everyone the same thing.
No channel preference, no send-time. Every customer gets the email, every customer gets the WhatsApp. Half feel spammed.
"Is this customer profitable?"
Retention curve says one thing. CAC says another. Without an LTV model that fuses both, you're guessing on each acquisition.
Ingest. Cohort. Predict. Surface.
Every event lands on the data plane, gets cohorted, and feeds the LTV models.
5 sources, one schema
Shopify orders, GA4 events, Google + Meta + TikTok ad metrics, GSC queries - all routed into a per-shop schema with explicit tenant scoping.
First-touch attribution
Customers cohort by first-touch month + acquisition channel + geography. Retention computed nightly out to 12 months.
LTV + channel + send-time
Gamma-gamma + BG/NBD per cohort. Bayesian per-customer channel preference. Send-time optimisation retrained weekly.
Query · webhook · export
Live UI for queries. Webhook export of LTV-changed events. BigQuery / Snowflake bulk export at Enterprise tier.
Five sources. One cohort engine. Four surfaces.
The exact runtime topology. Hover any node to inspect.
Three ways this earns its place.
Capability, not customer outcomes - we have none to report yet.
Predictive LTV at the cohort level
Cohort LTV is modelled with BG/NBD for purchase frequency and gamma-gamma for spend, rather than a trailing average dressed up as a forecast. The output is a per-cohort expectation with its inputs visible, so you can argue with the model instead of taking it on faith.
Channel and send-time per customer
Send-time and channel preference are inferred per customer by a Bayesian model retrained weekly, then wired into the comms pipeline. Blast-at-09:00 is the baseline it is measured against - on your list, in an A/B, not on a number we quote you.
One queryable rollup, every cohort
GA4 + Shopify + Google Ads + Meta + GSC streaming into one rollup. Per-shop schema isolation. Cohorts queryable by acquisition channel, first-touch month, geography, customer tier - all in one SQL surface.
What's available where.
| Capability | Starter | Pro | Agency | Enterprise |
|---|---|---|---|---|
| Shopify · GA4 · Ads · GSC ingest | ✓ | ✓ | ✓ | ✓ |
| Cross-channel revenue rollup | ✓ | ✓ | ✓ | ✓ |
| Cohort retention curves (12-mo) | - | ✓ | ✓ | ✓ |
| Channel preference (Bayesian per-cust.) | - | ✓ | ✓ | ✓ |
| Send-time optimisation | - | - | ✓ | ✓ |
| Predictive LTV (gamma-gamma + BG/NBD) | - | - | ✓ | ✓ |
| BigQuery / Snowflake export | - | - | - | ✓ |
| Model retrain cadence | - | wk | wk | daily |
See your data in one rollup.
We connect to your sources, build a cohort view in under 10 minutes, and walk through one channel-preference + LTV insight live.