Ask the question.
See the evidence.
Moby turns business questions into defensible analysis. It chooses the right data surface, validates the method, preserves your definitions, and returns the answer with its source attached.
Previous completed calendar month vs the month before.
calendar
Configured Summary definitions for MER and net margin.
source
Spend, order mix, COGS, discounts, and customer mix.
query
Separate marketing efficiency from margin pressure.
pending
Net margin declined as product mix and fulfillment costs moved against the gain.
Starts with the right source.
The agent does not force every question through one database. It routes the request to the surface that actually owns the metric.
Topline, configured costs, formulas, and executive KPIs.
summary surface
Widget-level analysis with known filters and dimensions.
dashboard widget
Breakdowns, joins, exports, custom windows, and reconciliation.
read-only query
Source, campaign, ad set, and ad contribution by selected model.
attribution page
Defined channel comparison against a similar-shop cohort.
peer cohort
One question. The whole business underneath it.
Ask in Moby. The agent can move from Summary metrics to warehouse tables to Pixel attribution without making you translate the question into dashboards or SQL.
Revenue, margin, customers, products, channels, campaigns, or the tension between them.
The source, table, model, date range, and validation steps remain visible while the agent works.
Refine the question, export the result, or drill into the next layer without starting the analysis over.
SQL that checks itself before it speaks.
For custom analysis, the agent inspects known-good patterns, validates the table and columns, executes read-only SQL, and checks coverage before interpreting the result.
WITH sum(ord.order_revenue) AS revenue, uniqExact(ord.order_id) AS orders SELECT ord.product_title, revenue, orders, revenue / nullIf(orders, 0) AS aov FROM orders_table AS ord WHERE ord.event_date >= '2026-05-01' AND ord.event_date < '2026-06-01' AND ord.is_new_customer = 1 GROUP BY ord.product_title ORDER BY revenue DESC
| Product | Revenue | Orders | AOV |
|---|---|---|---|
| Core set | $184,260 | 1,942 | $94.88 |
| Starter pack | $121,984 | 1,632 | $74.75 |
| Refill bundle | $93,115 | 1,073 | $86.78 |
| Travel size | $48,906 | 884 | $55.32 |
A warehouse built for questions, not table hunting.
Connected tools resolve into purpose-built analytical tables. The agent finds the right grain, validates fields and relationships, then queries only the surfaces needed to answer the question.
catalog
sales
delivery
search
flows
attribution
Attribution without sleight of hand.
Model, window, date basis, source, and drilldown level stay visible. The agent does not quietly swap a platform number for a Pixel-attributed one.
Compare performance in context.
See the period change, then understand whether it is an internal shift, a channel problem, or a gap versus similar businesses.
Store performance
2026-05-01 → 2026-05-31vs prior calendar month
One agent. The full analytical loop.
From a quick KPI read to a custom export, the same discipline follows the question all the way through.
Executive KPI snapshots
Load configured Summary sections for a period and explain the topline without rebuilding proprietary formulas.
snapshot
Period comparisons
Compare exactly two periods with calculated changes and the underlying values visible.
compare
Dashboard and widget analysis
Discover a named dashboard, inspect its widgets, apply the relevant filters, and retrieve focused data.
widget
Data warehouse + validated SQL
Inspect purpose-built tables, validate fields and relationships, run scoped SELECT queries, and save stable results for reuse.
SQL
Breakdowns and joins
Analyze products, customers, orders, campaigns, cohorts, and time windows with explicit grain and join logic.
scope
Stable exports
Create CSV-ready outputs, stabilize empty time series with a date spine, and preserve a usable schema.
artifact
Pixel attribution drilldowns
Move from all-channel source views into campaign, ad set, and ad detail using the selected model and window.
attribution
Peer benchmarks
Compare channel performance against a defined industry and GMV cohort without pretending it is a store KPI.
cohort
Metric validation
Preserve metric definition, source, timezone, date basis, attribution, population, and material filters.
ledger
Coverage and quality checks
Detect empty ranges, inspect availability bounds, check types, and retry once with a safer query shape when needed.
gate
Attribution-aware recommendations
Use Pixel contribution for media decisions and platform metrics as diagnostics, while checking current entity status.
first
Defensible explanations
Return the answer, what changed, why it matters, the exact evidence basis, and the limitation that could change the conclusion.
caveat
Every answer should survive the follow-up.
The goal is not a clever sentence. It is an answer another person can inspect, reproduce, challenge, and still use.
Exact about what it knows.
The agent is designed to reduce ambiguity, not hide it. When a definition, source, range, or join is uncertain, that uncertainty stays visible.
No silent metric mixing
Store truth, blended metrics, platform-native reporting, and Pixel attribution remain separate unless the analysis explicitly reconciles them.
No invented dashboard values
If a Summary metric is unavailable or returns N/A, the agent says so. A warehouse fallback is labeled as a different definition and scope.
No unvalidated SQL shortcuts
Tables and columns are inspected before new queries. Read-only execution, scoped dates, and exact grain are part of the workflow.
No attribution ambiguity
Model and window stay attached. “Linear” is clarified. “Total Impact” and click-plus-view wording map to their exact reporting models.
No pretending analysis is action
Forecasting, causal lift, creative production, and campaign mutations are separate workflows. Recommendations do not become changes without the owning action surface.