Compare this month with last by revenue and orders
The owner asks one question: better or worse, and by how much. Both months are counted by a single rule, with the caveats spelled out.
Easy · 15 min · once a month
What you get
May → June, revenue by shipment Metric May June Δ Revenue, ₽ 8,420,000 9,110,000 +8% Orders 3,180 3,210 +1% Avg order, ₽ 2,648 2,838 +7% Growth came from order value, not order count. But June had 21 working days against 19, and one 640,000 ₽ order accounts for a third of the gain.
A sample on made-up data — your numbers will be your own.
Who it fits
- Once a month the board needs the same table, counted the same way as last time.
- You want to know fast whether growth came from order count or order value — different stories.
When it won't work
The month isn't closed yet: some shipments and returns land later and the comparison drifts.
How the agent does it
Name months and rule
Say whether we count by shipment or by payment. Mixing the two bases shifts the answer by tens of percent on identical data.
Run the comparison
Both months go through one rule. Everything that makes them different — holidays, promos, working days — is listed separately, not averaged away.
Check before sending
Ask the agent to review its own work: where one large order created the growth, and where a percentage sits on a base too small to mean anything.
What you set
Connect Ozon, Wildberries and 1C. From you: which two months to compare and what counts as revenue — shipment or payment.
What you'll need
Starter prompt
Copy the prompt or open it straight in a chat with the agent.
Compare [month] with [the previous month] across Ozon, Wildberries and 1C sales. Show revenue, order count, average order value and returns — in total, by channel and by category. For each row give the change in rubles and in percent and state what produced it: more orders or a higher average order value. List separately everything that makes the months non-comparable: a different number of working days, marketplace promos, a large one-off order, unsettled returns. Show large one-off deals both in the total figure and as a separate "excluding one-offs" line. Count revenue by [shipment / payment] — the same way for both months. Output a comparison table and the five categories that drove most of the change.
Open in chatReview the comparison. List: — differences between the months unrelated to demand: working days, promos, holidays; — rows where the growth came from a single large order — show the figure without it; — categories where the comparison base is under [50] orders and the percentages mean nothing; — returns that belong to the previous month but landed in the current one; — which percentages were calculated off a small base and look bigger than they are.
A second prompt — the agent uses it to review its own work and show what's left for you.