Skip to main content
Nova Analytics
Try for free

How can I create an Amazon performance deck for a client call quickly?

To create an Amazon performance deck for a client call quickly, have an AI assistant read the client's live Amazon data and write one slide per question: how the week, month and year compare, which products moved, how advertising did, what is at risk, and how search share changed. Nova's MCP connector gives Claude, ChatGPT and other assistants that access to every client account an agency manages. Through Nova, the assistant pulls the figures with their comparisons, writes a title that states each finding, and closes with three actions for the coming week.

Updated

Connect your AI Copy the playbook

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 the day before each client call, once per client.

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

Use Nova to build this week's performance deck for one of my Amazon clients, ready for the client call.

Scope: the client I name, every marketplace of their accounts unless I name some, and the last complete week (Monday to Sunday).

1. Find the client. Call Nova's list_accounts and keep the accounts of the client I name. Say which accounts and marketplaces the deck covers, and whether they are Seller Central or Vendor Central.

2. Week slide. Call Nova's query_metrics with groupBy "marketplace", and sales, units, orders, sessions, conversionRate, adSpend, sponsoredSales, sponsoredTacos and netProfit, for the last complete week, with the week before as comparisonFrom and comparisonTo.

3. Month and year slide. Call query_metrics with the same metrics and no groupBy three times: month to date against the same days last month, month to date against the same days last year, and year to date against the same days last year.

4. Products slide. Call query_metrics with groupBy "childAsin", sortBy "sales", limit 10, and sales, units, adSpend and netProfit for the week against the week before. Then call Nova's find_movers with metric "sales", dimension "childAsin", direction "down", limit 5, over the same two weeks.

5. Advertising slide. Call Nova's query_advertising with groupBy "adProduct", adProducts sponsored_products, sponsored_brands, sponsored_brands_video and sponsored_display, and spend, sales, acos, orders, clicks and cpc, for the week against the week before.

6. Risks slide. Call Nova's query_inventory with groupBy "asin" and oosRiskFlag true, then Nova's query_listing_health sorted by severity, limit 20. Keep the products that sold in the last 30 days.

7. Search slide. Call Nova's query_sqp with grain "week", groupBy "period", queryTypes ["core"], and search_volume, your_impression_share and your_purchase_share, over the last 8 complete weeks. Say whether the client's share of their core searches rose or fell.

8. Build the deck. One slide per step from 2 to 7. Give each slide a title that states the finding, at most three bullets, and every figure with its comparison. Add a last slide with three actions for the coming week, each tied to a figure. If you can create files, return a slide file; otherwise return the slides as an outline I can paste into our template.

Rules: write for the client, with no internal notes. Relay every notice Nova returns before the figures it qualifies. Never add Seller Central and Vendor Central figures together. Say which figures are partial, such as traffic for the last two days. Never claim an action was taken.

Raw markdown

How Nova customers use this

Real requests from Nova customers, names removed.

  • “Build this week's client call deck: weekly performance, month to date against last month and last year, top products, listing health, stock at risk and search share.”

    What the assistant did

    A recurring weekly run, client by client: it resolved the client's account and marketplaces, then pulled one set of figures per slide, from the week-over-week table to the products with days of cover running low and the client's share of its core searches.

    Nova tools used (9)
    1. list_accounts
    2. query_metrics
    3. query_advertising
    4. query_listing_health
    5. query_inventory
    6. query_inbound_shipments
    7. query_reviews
    8. query_sqp
    9. query_search_terms

  • “Turn our weekly client deck into a skill the team can rerun for any client, and preview each slide's numbers.”

    What the assistant did

    It walked through the deck slide by slide on one client, previewed the week-over-week and month-to-date numbers, and checked whether a brand tag existed for a per-collection slide.

    Nova tools used (9)
    1. list_accounts
    2. list_tags
    3. query_metrics
    4. query_advertising
    5. query_search_terms
    6. query_listing_health
    7. query_inventory
    8. query_inbound_shipments
    9. query_sqp

  • “Office wall dashboard: sales so far today per client against the same day last week and last year, month and year to date, and the listings and stock that need attention.”

    What the assistant did

    It refreshed the dashboard through the day for weeks: sales per client and per marketplace against their baselines, traffic, conversion, organic share and returns per client, SKUs with 14 days of stock or less, and listings that sold recently but are now suppressed, not buyable or without the Buy Box.

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

  • “Nightly sync for our client dashboards: totals, traffic, campaigns, stock, inbound shipments and listing health for each client, checked against Nova before publishing.”

    What the assistant did

    Every night it pulled each client's figures for the dashboard pages and ran check totals over a fixed window, leaving out the latest days of traffic and of ad attribution until Amazon settles them.

    Nova tools used (8)
    1. list_accounts
    2. query_metrics
    3. query_advertising
    4. query_sqp
    5. query_inventory
    6. query_inbound_shipments
    7. query_listing_health
    8. query_subscribe_and_save

How do I show Amazon KPIs for all clients on one live dashboard?

Nova's Cockpit

How

Open the Global Workspace, which holds every connected account, set Group to Accounts, pick Compare to, then save the view

Refresh

As Nova's data updates

Google Sheets or a BI tool

How

Create a scheduled export with Split by Account and read its link with IMPORTDATA

Refresh

Every 3 hours

A dashboard your assistant builds

How

The assistant reads every account with query_metrics grouped by seller account and rebuilds the page

Refresh

As often as you schedule it

Every connected account sits in the Global Workspace, so an Admin sees all clients there, while each client workspace shows only its own accounts. An assistant connected to Nova reads every account its user can see in one call, and some Nova agencies run such a dashboard on an office screen through the day. The filters and views guide covers grouping and saved views, and the scheduled export guide covers the export link.

For a morning message instead of a screen, use the daily brief. For one client in depth, use the weekly business report. Amazon MCP for agencies explains how one connection covers every managed account.

How to read the result

Sales up, net profit flat

What it usually means

Growth came from ads or discounts

What to do

Show the TACOS and promotion lines next to it

Week down, month to date up

What it usually means

One weak week inside a good month

What to do

Lead with the month, explain the week

A top product on the risks slide

What it usually means

It may stock out or stop selling soon

What to do

Put it first on the actions slide

Search share falling on core searches

What it usually means

Competitors are taking the client's searches

What to do

Bring the ad and listing plan for those searches

Traffic marked as partial

What it usually means

Amazon has not published the last days yet

What to do

Compare conversion on complete days only

A slide with no data

What it usually means

The client has no ads, no Brand Analytics or nothing at risk

What to do

Drop the slide for that client

Limits

  • Amazon publishes traffic about two days late, so the last days of a week can read low.
  • Search Query Performance needs Brand Analytics, so it needs a registered brand.
  • Net profit is only as complete as the product costs entered in Nova for that client.
  • Nova does not send decks or reports by email. Run the playbook as a scheduled task in your assistant to have the deck ready before each call.
  • Written for Seller Central clients.
  • The assistant builds the deck from Nova's data. It does not change campaigns, prices or listings.

Questions sellers ask

Can I reuse the same deck for every client?

Yes. Save the playbook in your assistant, as a project instruction or a skill, and name a different client each run. Some Nova agencies build their weekly client decks this way, client by client.

Can Nova send the deck to my client?

No. Nova does not send reports by email. Run the playbook as a scheduled task in your assistant so the deck is ready before the call, then send it yourself.

Can each account manager see only their own clients?

Yes. Create one workspace per client and seat each Member in the clients they handle. Their Cockpit and their assistant then read only those accounts, while Admins see every account in the Global Workspace.