Skip to main content
Nova Analytics
Try for free

How AI can tell you if your Amazon deal made money

To know if an Amazon deal made money, the assistant needs live access to your discounts, deal fees, ads and costs, and Nova's MCP connector gives Claude, ChatGPT and other assistants that access to Seller Central and Amazon Ads. Through Nova, the assistant compares each product's profit during the deal with the weeks before, adds the deal fees Amazon books later, checks what happened after, and tells you which deals to repeat for Black Friday.

Updated

Connect your AI Copy the playbook
Example with made-up figures
Claude

Did last year's Black Friday deals make money?

NUsed Nova

In the deal week your three deals looked $770 ahead. Amazon then booked $1,090 of deal fees two weeks later, so they finished $320 behind. Repeat the mug set, cut the tumbler's 30% discount, and drop the tray. This is the likeliest read, not proof.

Ask anything

The playbook

Every step calls a Nova tool that reads your live Amazon data, so paste this into Claude, ChatGPT or any assistant connected to Nova's MCP server. Put in your deal dates, or leave them for last year's Black Friday week.

This needs an assistant connected to Nova. Start the 14-day free trial, then connect your assistant.

Use Nova to find out whether my Amazon deals made money, and which ones to repeat.

Deal period: [dates]. If I name none, use last year's Black Friday week, from the Monday before Black Friday to Cyber Monday.
Baseline: the same number of days right before the deal period.
After: the same number of days right after the deal period.
Fee window: from the first day of the deal to 21 days after its last day.

1. Check the costs first. Call Nova's query_metrics with netProfit for the deal period. If the answer carries cogsNotice, say what share of units has no cost before you quote any profit. If adsHistoryNotice says ad data starts after the deal, say that ad spend is unknown there.

2. Find the products. Call Nova's query_metrics with groupBy "childAsin", the deal period against the baseline, and the metrics units, netSales, netSalesPerUnit, productPromotions, adSpend, organicSales, netProfit and netProfitMargin, sorted by productPromotions, limit 30. A product counts as on deal if productPromotions rose or netSalesPerUnit fell. Some deals lower the price, so they show in netSalesPerUnit and not in productPromotions.

3. Read the fees Amazon books later. Call Nova's query_metrics with groupBy "childAsin" over the fee window, for those products, with the metrics dealParticipationFee, dealPerformanceFeeRollup, promotionRunLightningDealFee, couponParticipationFeeBase, couponPerformanceFee and couponRedemptionFee. Amazon can book these well after the deal, so the deal period alone can miss them. If the fee window has not ended yet, say the fees may be incomplete. Keep the sign each figure comes back with.

4. Work out the extra profit, per product. Take netProfit in the deal period, minus netProfit in the baseline. Then take off the fees from step 3 that fall outside the deal period, because netProfit in the deal period does not hold them. Show the result before and after those fees.

5. Read the discount. Discount share = productPromotions / (netSales + productPromotions). Also show the change in netSalesPerUnit against the baseline.

6. Check what ads did. From step 2, compare adSpend and organicSales with the baseline. Say whether the lift came with more ad spend or came organically.

7. Check what happened after. Call Nova's query_metrics with groupBy "childAsin", the after period against the baseline, with units and netSales. Then call Nova's query_bsr with groupBy "childAsin" for those products, the after period against the baseline. Say whether sales fell below the baseline after the deal, which suggests buyers came early, or held, and whether rank moved.

8. Check what else changed. Call Nova's list_events for the baseline, deal and after periods. Name any price, content or PPC change that could explain the result.

9. Check you can run it again. Call Nova's query_inventory with groupBy "asin" for the products you would repeat. Give days of inventory and inbound units against the units sold in the deal period.

10. Report, one row per product: discount, units against the baseline, extra profit before and after fees, ad spend change, what happened after, and a verdict: repeat, change the discount, or drop. Then give the total before and after fees, and the one change you would make for the next event.

Rules: these are correlations, so never state a cause as proven. Events like Black Friday lift demand anyway, so say that the baseline can flatter a deal. Say which figures are missing and why. Relay every notice Nova returns (P&L rules, marketplaces added up, COGS gaps, currency, ad history). You cannot create deals or change prices.

Raw markdown

How Nova customers use this

Real requests from Nova customers, names removed.

  • “Last 30 days against the prior 30 per ASIN, in stock only, to flag slow sellers for Black Friday promotions.”

    What the assistant did

    It read stock first, then compared units, sales and sessions per ASIN per marketplace.

    Nova tools used (3)
    1. query_inventory
    2. query_metrics
    3. query_listing_health

  • “A margin and inventory based Black Friday discount proposal, per product.”

    What the assistant did

    It checked cost coverage, read stock and cover, current prices and landed costs, then compared the last 30 days with the 30 before.

    Nova tools used (6)
    1. list_accounts
    2. list_metrics
    3. query_inventory
    4. query_listing_health
    5. get_cogs_worksheet
    6. query_metrics

  • “Per-ASIN unit economics to model an event discount, with the uplift from past Prime events to calibrate volume.”

    What the assistant did

    It read margin per ASIN, then the sales lift at earlier events per account.

    Nova tools used (3)
    1. list_accounts
    2. list_metrics
    3. query_metrics

  • “Best Seller Rank during Prime Day against the 3 weeks before, and after, with logged price, PPC and content changes checked first.”

    What the assistant did

    It checked what else changed, then compared rank before, during and after.

    Nova tools used (3)
    1. list_accounts
    2. list_events
    3. query_bsr

  • “Daily net sales across marketplaces for the deal week against the week before, then whether a weak uplift repeats at a second event.”

    What the assistant did

    It compared marketplaces, checked whether rank moved on the deal days, then repeated the test on an earlier event.

    Nova tools used (3)
    1. query_metrics
    2. query_bsr
    3. query_sqp

What did the deal really cost?

A deal costs more than the discount. productPromotions holds the discounts customers got on coupons, deals and lightning offers. Some deals lower the price instead, so they show in netSalesPerUnit.

Then come the fees: dealParticipationFee, dealPerformanceFeeRollup, promotionRunLightningDealFee, couponParticipationFeeBase, couponPerformanceFee and couponRedemptionFee, per product. Nova's P&L puts them next to cost of goods, Amazon fees and ad spend, so netProfit is what is left.

Why do deal fees show up after the deal?

Amazon books them later. In Nova's records of Prime Day and Prime Big Deal Days 2026, deal fees landed about two weeks after the event. So a profit report on the deal's own dates can look better than the deal really was.

The playbook reads fees for 21 days after the last day of the deal, and shows profit before and after them.

Compared with what?

The playbook compares the deal with the same number of days right before it. That is a fair start for a normal week and a generous one for Black Friday, when demand rises whatever you do. So the assistant says the baseline can flatter a deal, and it checks list_events for any price, content or PPC change in the same weeks.

Did the deal help after it ended?

A deal can pull next week's buyers forward. If units fall below the baseline after the deal, that is what to suspect. If they hold and query_bsr shows a better rank, the deal may have helped beyond its dates. Neither is proof.

Which deals should I repeat for Black Friday?

Start from what each deal earned after fees, then check you hold the stock to run it again.

Extra profit stays positive after fees, sales hold after the deal

What it usually means

The deal paid for itself

What to do next time

Repeat it

Extra profit positive before fees, negative after

What it usually means

The fees took the gain

What to do next time

Lower the discount or pick a cheaper deal type

Units up, profit down, sales below the baseline after

What it usually means

Buyers came early

What to do next time

Shorten it or drop it

Lift came with higher adSpend, flat organicSales

What it usually means

You bought the lift

What to do next time

Judge it with the ads included

Rank better after the deal and sales above the baseline

What it usually means

The deal may have helped beyond its dates

What to do next time

Check again a month later before you repeat it

Stock ran out during the deal

What it usually means

The lift was capped

What to do next time

Fix stock before you repeat it

query_inventory gives days of inventory and inbound units per product today.

Example with made-up figures

A Black Friday week, worked through

Three products on deal, over eight days, against the eight days before.

Ceramic mug set

Discount

20%

Units before

200

Units in the deal

640

Profit before

$1,400

Profit in the deal

$2,250

Fees booked later

$380

Extra profit

+$470

Verdict

Repeat

Travel tumbler

Discount

30%

Units before

150

Units in the deal

700

Profit before

$1,200

Profit in the deal

$1,050

Fees booked later

$450

Extra profit

-$600

Verdict

Change the discount

Bamboo tray

Discount

15%

Units before

90

Units in the deal

130

Profit before

$540

Profit in the deal

$610

Fees booked later

$260

Extra profit

-$190

Verdict

Drop

In the deal week the three looked $770 ahead. Amazon then booked $1,090 of deal fees two weeks later, so they finished $320 behind. The mug set held its sales after the deal. The tumbler sold 700 units at a loss against the week before, and its sales fell below the baseline after, so buyers came early. The tray barely moved.

Can I work this out in a spreadsheet?

You can, but it takes several Seller Central reports: orders, promotions, ads and the payments report for the fees, joined per product by hand, with your own costs added on top. Fees booked two weeks later fall outside a report on the deal's dates, so they are easy to miss. With Nova the assistant reads all of them per product, for any dates.

What this cannot tell you

  • Nova shows what moved at the same time as the deal. It does not prove what the deal caused.
  • A few fees come back with no product on them. Read those at account level.
  • Stock is the state today, not a history, so it cannot show a stockout during last year's deal. Units falling to zero point to one.
  • A deal that overlaps another promotion cannot be separated from it.
  • Ad data starts about 60 days before you connected Amazon Ads, and ad spend reads 0 before that.
  • A trial reads 3 months of orders, fees and returns. Last year's Black Friday needs a paid plan's 2-year history.
  • This playbook is built for Seller Central. It does not create deals or change prices.

For a single product that fell, see why your Amazon sales dropped. For ad spend that never sold, see wasted PPC spend.

Questions sellers ask

Does Nova show Amazon deal and coupon fees per product?

Yes. Deal participation and performance fees, Lightning Deal fees and coupon participation, performance and redemption fees each have their own line, per SKU and ASIN, and a few come back with no product attached. They sit in the P&L with your other costs.

How do I measure the real profit of a Lightning Deal or coupon?

Take the product's profit during the deal, compare it with the same number of days before, then take off the fees Amazon books after the deal. The playbook does this per product, and shows the result before and after those fees.

Why does my discount not show in promotions?

Some deals lower the price instead of applying a promotion. Then the discount shows in net sales per unit, so the playbook reads both.

Can it read last year's Black Friday?

Yes, on a paid plan, which reads 2 years of history. A trial reads 3 months of orders, fees and returns. Ad data starts about 60 days before you connected Amazon Ads.

Does this create deals or change my prices?

No. Every tool in this playbook only reads. You create deals and change prices in Seller Central. The connection uses OAuth, per account, and you can revoke it at any time.

Does this work for Vendor Central?

This playbook is built for Seller Central. For Vendor Central, see the Vendor Central prompts.

Ask your assistant which deals made money

Connect your AI