BoostEcom AgencyBoostEcom AgencyTheme Copilot AITheme Copilot AIPageBuilder.StorePageBuilder.StoreYour brand hereYour brand here
OrbitOrbitEasyConnector.appEasyConnector.appYour brand hereYour brand here
Loading session…
Features

Store Intelligence.

The live Shopify ecosystem graph. Deep-scan probes turn any public storefront into a canonical record (stack, ads, traffic, reviews, emails) that the Hub ranks and every agent reads.

Live graph34 probe modulesLive store searchEstimates flagged

Definition

What it is

Store Intelligence is the data engine behind the store search in BoostEcom OS, in your dashboard. 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. It lives in BoostEcom OS, not in a separate tool.

Browse and rank live in BoostEcom OS, in your dashboard. This page tells the product story; the old /intelligence/* category hubs redirect here. Prediction and market clusters exist as experimental crons: estimates stay flagged.

Public inspectors
4
Public data only
100%
Plugs into your own AI
MCP
Cost to inspect a store
$0

Four public doors

Your store

Standing audits of your own store.

A System is a standing audit of one part of your store. It reads real data rather than opinions, it scores what it finds, and it hands @Atlas something to act on instead of a PDF you file.

SEO and Conversion are Beta skill compositions. Tracking is free without an account at /scan/tracking. AEO, AOV and Web Vitals already expose @Atlas tools.

Scenario 1Simulated
Are my pixels firing on checkout?
@AtlasThat needs a live look, so I am running the tracking scan: a real browser walks your storefront to checkout and lists every pixel that fires. Want the report on your store's Tracking page?
In practice

Every figure says where it comes from

Observed, estimated or absent: @Faye labels each number in the sentence that carries it. These three answers replay the fixture the product is tested against.

Scenario 2Simulated
How much is competitor.example making per month?
@FayeOur review-velocity model puts it at about $48,000 a month. That is an estimate: the store does not publish its revenue. Want me to track it weekly?
Scenario 3Simulated
How many products does competitor.example sell?
@Faye214 products, read from its public product feed. Want the ones added this month?
Scenario 4Simulated
What is competitor.example spending on ads?
@FayeThat figure is not available: no public source shows it, and I will not derive one from the revenue estimate. I can list the ads they run instead. Want that?
The mechanism

How it works

From public probes to the graph @Atlas reads back.

  1. Probes read the store

    Deep-scan probes read public signals: catalog, theme, apps, pixels, ads, reviews, social, emails.

  2. Canonical record

    Each domain rolls up into one canonical record with layered confidence (ground truth / observed / estimated).

  3. Store search

    BoostEcom OS, in your dashboard, searches, filters and ranks that graph in real time.

  4. Single-probe inspectors

    Single-probe inspectors (theme detector, ads spy…) answer one question at a time.

  5. Same graph for the agent

    @Atlas and the MCP server read the same graph, so research turns straight into action.

The scope

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 labeled 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 honor it. The same rule protects yours.

What we will not invent

  • Estimates are marked. Revenue and traffic guesses stay labeled. They are not accounting.
  • Opt-out exists. Transparency explains how a store leaves the index.

Shipped but not the headline

  • Prediction and market-cluster crons exist. They stay experimental, not a headline feature.

Transparency

Your AI client

Ask it from the AI client you already use

The MCP server brings this surface into your own assistant, with the same store and the same memory. Each client has its connect guide.

Jobs

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 when. Reach for Store Intelligence when you need to understand a competitor, validate a niche, or find the stores and angles that are scaling. Browse and act from BoostEcom OS in your dashboard; drop into an inspector when you only need one signal.
  • Do not use it when. When you need an accounting figure: revenue and traffic are estimates flagged as such, not financial statements.
Store Intelligence

Questions people ask

Where does the data come from?
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?
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?
Newly discovered stores fill in over time. A first scan is shallower than an already-warm record.
How do I get out of the graph?
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?
@Atlas and the MCP server read the same graph as the Hub, so a search turns directly into action on your own store.

A question that is not here?

Ask it, and it joins this page if it comes back.

See all features