Skip to main content
Nova Analytics
Try for free

How to use AI to know what to reorder on Amazon before you run out

To know what to reorder on Amazon, the assistant needs live access to your stock, inbound shipments, lead times and margins, and Nova's MCP connector gives Claude, ChatGPT and other assistants that access to Seller Central. Through Nova, the assistant ranks what runs out first, checks what is on its way, reads the margin behind each product, and tells you how many units to order, or not to.

Updated

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

What do I need to reorder this week?

NUsed Nova

Two products need a decision. The knife block has 9 days of stock and nothing inbound, and its order is already 12 days late. The bamboo tray has 12 days left but loses money, so fix that before you reorder. Serving trays hold 140 days. These use your lead times, except the tray, which runs on Nova's defaults.

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. Run it weekly, 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 tell me what to reorder on Amazon, how much, and what not to reorder.

1. Read what runs out first. Call Nova's query_inventory with groupBy "asin", includeReorder true, oosRiskFlag true, sorted by daysOfInventory, sortOrder "asc", limit 30. Give days of inventory, days of supply after inbound, sales velocity, and units on hand. Never add the non-Pool quantities across SKUs.

2. Check the parameters. Each row gives lead times and targets, with a source for each. If a source says fleet_default, or paramsTyped is false, say the recommendation uses Nova's defaults and not my own lead times. If recoStatus is params_missing, say nothing is assumed and ask me for lead times.

3. Check what is on its way. Call Nova's query_inbound_shipments with category "in_progress", then "planned". Planned shipments are still with me, so they are not inbound yet. Then call it with category "closed_incomplete" to see shipments that came up short.

4. Read the worth of each product. Call Nova's query_metrics with groupBy "childAsin", the last 90 days, with units, netSales, netProfit and netProfitMargin. If cogsNotice appears, say what share of units has no cost before you quote profit.

5. Check that velocity is real. Call Nova's query_metrics with groupBy "week" over the last 8 complete weeks for the top 5 products, with units. A week at or near zero points to a stockout, so velocity may understate demand. If the next weeks hold a peak, compare the same weeks last year.

6. Check the listing. Call Nova's query_listing_health for those products. Do not recommend stock for a listing that cannot sell.

7. Read the order. From step 1, give recommendedOrderQty, daysUntilReorder (negative means late), coverageTotal, recommendedOrderWeightKg and recommendedOrderVolumeCbm. Subscribe & Save deliveries are in snsForecastUnits30d, so read them next to days of inventory.

8. Report, one row per product: days left, inbound, margin, units to order, and a verdict: order now, order this month, hold, or do not reorder yet. Say why for any product that loses money. Then the total units and freight weight.

Rules: stock is the state today. Do not recommend reordering a product only because it is low: read its margin first. Say which figures are missing and why, and relay every notice Nova returns. You cannot place orders or create shipments.

Raw markdown

How Nova customers use this

Real requests from Nova customers, names removed.

  • “Daily brief: active SKUs under 14 days of cover or out of stock.”

    What the assistant did

    A recurring stock check in a daily brief.

    Nova tools used (1)
    1. query_inventory

  • “Market purchase trend on core search queries, to refine a shipment size for the holidays.”

    What the assistant did

    It read current stock, the weekly sales trend and last year's seasonality, then the market's trend on the core queries.

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

  • “Scheduled inventory monitoring: stock levels and days of cover, shipments in transit and planned, and SKUs with 14 days of cover or less.”

    What the assistant did

    A scheduled run across two seller accounts, reading stock, then inbound and planned shipments, then flagging stockout risk.

    Nova tools used (2)
    1. query_inventory
    2. query_inbound_shipments

  • “Weekly FBA shipment plan: an at-risk shortlist, whether last week's recommended shipment left, and 12-month profitability on the shortlist.”

    What the assistant did

    It built the shortlist, checked inbound for last week's shipment, then read profit and 90-day velocity per product.

    Nova tools used (5)
    1. list_accounts
    2. query_inventory
    3. query_inbound_shipments
    4. query_metrics
    5. query_listing_health

  • “Current FBA stock and 30-day velocity, to build a Q4 inventory forecast.”

    What the assistant did

    It read stock and velocity, then checked listing status on SKUs missing from the stock list to tell active from discontinued.

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

  • “Weekly unit series for top ASINs, to date last month's stockouts for a monthly deck.”

    What the assistant did

    It read stock positions going into the quarter, then the weekly units to date each stockout.

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

What runs out first?

query_inventory gives days of inventory per product, from sellable units and the last 30 days of sales. projectedDaysOfInventory adds reserved, inbound and any AWD stock. oosRiskFlag marks anything under 35 of those days, so the list shows what is still short once the inbound lands.

What is already on its way?

query_inbound_shipments splits shipments into planned, in progress, closed short and closed complete. Planned ones are still with you, so they are not inbound yet. Closed short lists shipments where Amazon received fewer units than you shipped. Amazon's inbound API gives no dates, so this shows the state and not an arrival day.

Is this product worth reordering?

Low stock is not a reason on its own. query_metrics reads units, net sales, net profit and margin per child ASIN. A product that loses money is one to fix before you buy more of it. A low-margin product with months of stock is cash parked in the warehouse.

How many units should I order?

With includeReorder, each row gives recommendedOrderQty: sales velocity times your lead times and targets, minus everything already in the pipeline, rounded up to the case pack. It also gives daysUntilReorder, coverageTotal, and the freight weight and volume. Each row says whether the lead times are yours or Nova's defaults.

Few days left, nothing inbound, good margin

What it usually means

Lost sales ahead

What to do

Order now, and consider air for part of it

daysUntilReorder negative

What it usually means

The order is already late

What to do

Order now, and plan the gap

Few days left, negative margin

What it usually means

Stock would keep a loss going

What to do

Fix price or cost first

Many days of stock, low velocity

What it usually means

Cash parked in the warehouse

What to do

Hold, and check storage fees

Weeks at zero units in the series

What it usually means

A past stockout

What to do

Read velocity from the weeks before it

recoStatus is params_missing

What it usually means

Nova has no lead times for it

What to do

Enter them, because nothing is assumed

Example with made-up figures

A reorder list, worked through

Knife block

Days of stock

9

Inbound

0

Margin

24%

Units to order

600

Verdict

Order now: 12 days late

Cutting board

Days of stock

28

Inbound

400

Margin

18%

Units to order

250

Verdict

Order this month

Bamboo tray

Days of stock

12

Inbound

0

Margin

-4%

Units to order

180

Verdict

Do not reorder yet: it loses money

Serving trays

Days of stock

140

Inbound

0

Margin

6%

Units to order

0

Verdict

Hold

Can I do this from Amazon's restock report?

You can start there. It does not know your margin, your own lead times, stock in your warehouse or your supplier orders, so it cannot tell you what is worth reordering. With Nova the assistant reads those next to Amazon's stock, if you entered them.

What this cannot tell you

  • Stock is the state today, not a history. Weeks of units are the way to date an old stockout.
  • Velocity reads the last 30 days, so a recent stockout or peak skews it.
  • Inbound shipments carry no dates, because Amazon's inbound API gives none.
  • Stock outside Amazon and supplier orders count only if you entered them in Nova.
  • The recommendation uses your lead times and targets, or Nova's defaults where you set none, and each row says which.
  • Nova does not place orders or create shipments.
  • This playbook is built for Seller Central.

To see this in the app, see FBA inventory. For products already falling, see why your Amazon sales dropped.

Questions sellers ask

How does AI know what to reorder on Amazon?

It needs your stock, velocity, inbound, lead times and margin. Through Nova the assistant reads all of them, ranks what runs out first and gives the units to order, or says why not to.

Does it count stock in my own warehouse?

Yes, if you entered it in Nova, along with supplier orders. Stock counts from a 3PL or your warehouse appear as external stock, and coverage is shown with and without them.

Does it use my lead times?

Yes, once you enter them. Until then it uses Nova's defaults where they exist, and each row says which source it read.

Can it include FBM stock?

Yes. Pass includeFbm to count merchant-fulfilled stock as backup in days of inventory.

Does it place orders or create shipments?

No. Every tool in this playbook only reads. The connection uses OAuth, per account, and you can revoke it at any time.

Ask your assistant what to reorder this week

Connect your AI