All use cases

See where sales dropped on WB and Ozon

The month closed below plan and the reason won't surface: fewer orders, or lower prices? Ozon and Wildberries get read separately, factor by factor.

Medium · 25 min · once a week

What you get

Revenue drop, March: −18% (−1,240,000 ₽)
Ozon     −6%   price down, orders flat  −310,000 ₽
WB      −27%   2,100 fewer orders       −930,000 ₽
Top 3 items behind the drop:
  ART-4471  −340,000 ₽  14 days out of stock
  ART-2210  −210,000 ₽  priced 12% below last month
  ART-9008  −155,000 ₽  returns 9% → 21%
Excluded: 240,000 ₽ from SKUs you marked clearance

A sample on made-up data — your numbers will be your own.

Who it fits

  • Revenue fell, but in each dashboard on its own everything looks "roughly as usual".
  • You need to separate a general demand dip from problems with specific listings — the fixes differ.

When it won't work

The operating model changed mid-period: FBS to FBO, or a new legal entity. Before and after aren't comparable.

How the agent does it

1

Pick the comparison period

The agent reads both dashboards itself. Say what we compare against: last month, or the same month a year ago — the conclusions differ.

2

Run the breakdown

Each marketplace is counted on its own, and the drop is split into price, quantity and returns. Not one combined number, but what made it.

3

Check the conclusions

Ask the agent to review its own work: where a conclusion rests on five orders, and where an item was simply out of stock and that got read as weak demand.

What you set

Connect Ozon and Wildberries. From you: the period, what to compare against and the items to leave out — clearance stock, discontinued lines.

What you'll need

Ozon
Wildberries

Starter prompt

Copy the prompt or open it straight in a chat with the agent.

Prompt for the agent

Merge Wildberries and Ozon sales for [period] and compare with [the previous period / the same period last year]. For each marketplace, category and SKU show revenue, orders, average order value and returns. Break every decline down into factors: order count fell, selling price fell or returns grew — and show each factor's contribution in rubles. Don't explain a decline by "falling demand" or "seasonality" until you show a figure that confirms it. If an item didn't sell because it was out of stock, say exactly that — that isn't a demand decline. Output a SKU table sorted by lost revenue, and the ten items that account for half of the decline.

Open in chat
Check the result

Review the analysis. List: — SKUs where the decline was calculated on fewer than [30] orders in one of the periods; — items that were out of stock, and this got confused with a demand decline; — comparisons where the periods have a different number of days or a different number of marketplace promos; — cases where revenue fell but margin grew — that isn't a problem; — which explanations of the decline you confirmed with a figure and which remain hypotheses.

A second prompt — the agent uses it to review its own work and show what's left for you.

Related use cases