@Atlas audits the catalog the day the store is connected and ships a CRO plan, instead of handing back a list of things to go read. Audit to plan, same session.
BoostEcom DemoDemo
Founder
Intelligence.
The live Shopify ecosystem graph. Twenty-plus deep-scan probes turn any public storefront into a canonical record (stack, ads, traffic, reviews, emails) that powers Store Spy and feeds every agent.Live graph30+ probesHub SpyEstimates flagged
The numbers
Intelligence surfaces
- Public inspectors
- 4
- Public data only
- 100%
- Plugs into your own AI
- MCP
- Cost to inspect a store
- $0
What it is
Intelligence is the data engine behind BoostEcom's Store Spy. It continuously scans the public Shopify ecosystem and maintains one canonical record per domain, layered with confidence levels, so operators and @Atlas can research any store and act on what they find. The engine itself lives in the BoostEcom OS Hub. Not a separate tool.
Browse and rank live in the Hub OS Spy list. This Features page is the product story; /intelligence/* category hubs redirect here. Prediction and market clusters exist as experimental crons: estimates stay flagged.
Four public doors
- Hub SpyThe live browse/rank surface on the home OS Hub.
- InspectMono-probe tools under /intelligence/inspect.
- RadarMoving signals across the graph.
- TransparencyMethod, provenance and opt-out. Start here before you trust a number.
How it works
From public probes to the graph @Atlas reads back.
- Twenty probesTwenty-plus deep-scan probes read public signals. Catalog, theme, apps, pixels, ads, reviews, social, emails.
- Canonical recordEach domain rolls up into one canonical record with layered confidence (ground truth / observed / estimated).
- The Store SpyStore Spy in the OS Hub searches, filters and ranks that graph in real time.
- Single-probe inspectorsSingle-probe inspectors (theme detector, ads spy…) answer one question at a time.
- Same graph for the agent@Atlas and the MCP server read the same graph, so research turns straight into action.
What Intelligence is for
- Peer setsFind stores that share stack, creatives or tracking ids.
- Creative intelAds and angles extracted from real storefronts.
- Agent accessAPI keys and the Intelligence MCP, reading the same graph.
When to use it
- Use it whenReach for Intelligence when you need to understand a competitor, validate a niche, or find the stores and angles that are scaling. Browse and act from Store Spy in the OS Hub; drop into an inspector when you only need one signal.
- Do not use it whenWhen you need an accounting figure: revenue and traffic are estimates flagged as such, not financial statements.
What we will not invent
- Estimates are markedRevenue and traffic guesses stay labelled. They are not accounting.
- Opt-out existsTransparency explains how a store leaves the index.
What it covers, what it doesn't
What this covers, and what it leaves to something else. Knowing beforehand costs less than finding out after.
- Public data only. Nothing behind a login, a paywall or a private API.
- Revenue and traffic are estimates computed from public signals, and labelled as such. Use them to rank and compare, not to invoice.
- A newly discovered store starts shallow and deepens with each pass. The first record is thinner than a warmed one.
- Any store owner can opt out from the transparency page, and we honour it. The same rule protects yours.
Shipped but not the headline
- Prediction and market-cluster crons exist. They stay experimental edge, not a Features headline.
The neighbouring features
Same family, same product surface.
Where does the data come from?Intelligence
Public sources only. Nothing behind a login, nothing behind a paywall. Any store can opt out at any time from the transparency page.
Are the revenue figures accurate?Intelligence
They are estimates, marked as such. Each layer carries its confidence level: ground truth, observed, or inferred. We never present an estimate as a fact.
Why does a store have little data?Intelligence
Newly discovered stores fill in progressively. A first scan is shallower than an already-warm record.
How do I get out of the graph?Intelligence
Through the transparency page, which sets out the opt-out procedure. It is open to any store, customer or not.
What is it actually for?Intelligence
@Atlas and the MCP server read the same graph as the Store Spy, so a search turns directly into action on your own store.
One operator, the full stack: Maya runs the email calendar, Marco curates collections, Otis watches fulfilment. One team, one thread.
BoostEcom DemoDemo
Head of Growth
The work gets done rather than suggested. Voice mode with @Atlas turns the morning check-in into a conversation. It operates.
BoostEcom DemoDemo
Store owner
@Maya rewrites product descriptions, queues them for review, pushes the approved batch live, then runs the campaign around them. End-to-end, with approval gates.
BoostEcom DemoDemo
E-commerce lead
Every action the AI Team takes is graded against real Shopify Analytics after the observation window closes. Outcome attribution, not vibes.
BoostEcom DemoDemo
Marketing lead
OAuth scopes, audit log, store-scoped credits, no shadow data. The agents work inside the admin, not around it.
BoostEcom DemoDemo
Engineer
Permission mode decides what ships on its own and what waits for a human. Autonomy you dial in.
BoostEcom DemoDemo
Operator
Multi-store from one console, each with its own connectors, memory and budget. Per-store context.
BoostEcom DemoDemo
Agency owner
@Atlas audits the catalog the day the store is connected and ships a CRO plan, instead of handing back a list of things to go read. Audit to plan, same session.
BoostEcom DemoDemo
Founder
One operator, the full stack: Maya runs the email calendar, Marco curates collections, Otis watches fulfilment. One team, one thread.
BoostEcom DemoDemo
Head of Growth
The work gets done rather than suggested. Voice mode with @Atlas turns the morning check-in into a conversation. It operates.
BoostEcom DemoDemo
Store owner
@Maya rewrites product descriptions, queues them for review, pushes the approved batch live, then runs the campaign around them. End-to-end, with approval gates.
BoostEcom DemoDemo
E-commerce lead
Every action the AI Team takes is graded against real Shopify Analytics after the observation window closes. Outcome attribution, not vibes.
BoostEcom DemoDemo
Marketing lead
OAuth scopes, audit log, store-scoped credits, no shadow data. The agents work inside the admin, not around it.
BoostEcom DemoDemo
Engineer
Permission mode decides what ships on its own and what waits for a human. Autonomy you dial in.
BoostEcom DemoDemo
Operator
Multi-store from one console, each with its own connectors, memory and budget. Per-store context.
BoostEcom DemoDemo
Agency owner
A question that is not here?
Ask it, and it joins this page if it comes back.