Skip to main content

A daily Amazon brief with anomaly alerts

To get a daily Amazon brief with anomaly alerts from AI, the assistant needs live access to yesterday's sales, ads, stock and listings, and Nova's MCP connector gives Claude, ChatGPT and other assistants that access to Seller Central and Amazon Ads. Through Nova, the assistant compares yesterday with the same day last week, flags the products that moved more than usual, explains each one, and names the stock and listing risks to handle today.

Updated

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. Run it each morning, or on a schedule if your assistant supports scheduled tasks.

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

Use Nova to write my daily Amazon brief for yesterday and flag anything unusual.

Day: yesterday. Baseline: the same weekday last week, so weekday patterns do not read as alerts.

1. Scoreboard. Call Nova's query_metrics for yesterday against the baseline with netSales, units, netProfit, adSpend, sponsoredAcos and sponsoredTacos. Then the same for the last 7 days against the 7 days before. If a figure for yesterday is still incomplete, say so rather than reading it as a drop.

2. What moved. Call Nova's find_movers on netSales for yesterday against the baseline, direction "down", dimension "childAsin", limit 5. Then direction "up". Ignore rows with an empty id or __UNALLOCATED__.

3. Flag anomalies. Flag a product when its net sales moved more than 30% and more than a tenth of yesterday's total change. Flag the account when ad spend rose more than 25% while sponsored sales did not.

4. Explain the flags. For each flagged product, call Nova's explain_movement for yesterday against the baseline. Say whether price, Featured Offer share, promotions, ad spend or clicks moved with it.

5. Stock. Call Nova's query_inventory with oosRiskFlag true, sorted by daysOfInventory ascending, limit 10. Name what runs out within 14 days.

6. Listings. Call Nova's query_listing_health with bands [0, 1], sort "severity", limit 10. Name any suppressed or blocked top seller.

7. What changed. Call Nova's list_events for the last 2 days.

8. Write the brief, under 200 words: one line on yesterday, the scoreboard, the flags with their likely cause, stock and listing risks, and the one thing to do today.

Rules: these are correlations, so never state a cause as proven. Leave out anything that is normal. Say which figures are missing and why, and relay every notice Nova returns. Edit a Seller Central listing only when I ask and an Admin or Workspace owner confirms the preview. Never change prices, stock or advertising.

Raw markdown

How Nova customers use this

Real requests from Nova customers, names removed.

  • “Every morning: listing status and Buy Box per SKU, inbound shipments, stock cover, the biggest sales movers, and keywords spending with no orders.”

    What the assistant did

    A recurring daily run: it checks listings, inbound and stock, finds the SKUs whose sales moved most week over week, explains each fall through traffic, conversion, Buy Box and ads, then lists the ad leaks.

    Nova tools used (6)
    1. query_listing_health
    2. query_inbound_shipments
    3. query_inventory
    4. find_movers
    5. explain_movement
    6. query_advertising
  • “Daily ads pass: yesterday against the day before per SKU, the last 7 days by campaign, and bid cut or negative candidates.”

    What the assistant did

    A recurring daily run: it compares SKUs day over day, reads campaigns over 7 days, flags keywords with spend and no sales, and checks stock cover and open shipments on a product being restocked.

    Nova tools used (4)
    1. query_metrics
    2. query_advertising
    3. query_inventory
    4. query_inbound_shipments
  • “Check for past-due purchase orders, open POs at risk of cancellation, and suppressed listings that need a fix today.”

    What the assistant did

    It listed past-due Vendor Central POs and the open POs with the soonest ship windows, then the suppressed or degraded listings.

    Nova tools used (3)
    1. query_vendor_purchase_orders
    2. query_listing_health
    3. list_accounts

How to read the result

Sales down on one product, Featured Offer share down

What it usually means

Another offer took the Buy Box

What to check

The Buy Box loss playbook

Ad spend up, sponsored sales flat

What it usually means

Bids or budgets rose without return

What to check

Campaigns and search terms in Amazon Ads

Sales down across the account, no single product

What it usually means

Demand or a site-wide issue

What to check

The same day last year, list_events

Top seller under 14 days of stock

What it usually means

Lost sales ahead

What to check

Inbound shipments and the reorder playbook

Suppressed top seller

What it usually means

The listing cannot sell

What to check

Seller Central's listing quality page

Limits

  • Yesterday's figures move for a few days as orders, ads and traffic finish loading. Sessions and conversion refresh once a day.
  • The thresholds in step 3 are a starting point: change them to suit your account.
  • Stock and listing health are the state today, not a history.
  • Nova reads your data and can edit a Seller Central listing when you ask and an Admin or Workspace owner confirms the preview. Prices, stock and advertising never change through the assistant.