by Audra Carpenter

Project inventory and recommend when to reorder each product

Have Claude Code pull inventory and sales data, project the next twelve months of sales and stock by product, and recommend when to reorder each one, using written notes on supplier lead times and holidays.

What the agent did

Source-reported example · as described by Alex Willen (acquires and operates Amazon e-commerce brands; author of The Automated Operator)

The author, who acquires and operates e-commerce brands selling on Amazon, had Claude Code build scripts to pull inventory and sales data for each brand, then talked through each brand's context (acquisition dates, inventory at a 3PL, supplier lead times, supplier locations), which Claude saved in a file per brand.

Asked to review the data first, Claude picked out anomalously low sales months and very-low-stock items with no inbound units, and the author explained them. Claude then produced inventory projections and reorder recommendations for each brand.

After a day of correcting its method, the author set up an /inventory command whose instructions have Claude refresh stale Amazon data, read the brand's context notes, show trailing-twelve-month sales by SKU and month, state its adjustment factors, project next-twelve-month sales and month-end stock using Python, and recommend when to reorder each SKU, factoring in Chinese New Year and other holidays.

Per the post, Claude also asked whether an inbound Amazon shipment had come from the 3PL and whether to adjust the 3PL stock count.

Reported: the author says that since setting up the /inventory command he has "not once used a spreadsheet for this task" and uses it consistently. Reported: initial setup took half a day, and the first projections were "very bad", followed by a day-long cycle of corrections. No figures on time saved, stockouts avoided or forecast accuracy are given.

Limitations

The first projections were wrong: Claude underestimated seasonality, sometimes ignored the CLAUDE.md note, copied last year's sales unchanged, and made math errors that led to wrong reorder recommendations; the author added explicit steps to the command to fix each problem.

Even after it noted feedback, it often repeated the same mistake. It recommends reorder timing only; it does not place orders with suppliers.

The scripts and the full instruction file are not published, and the number of brands and SKUs isn't stated. No accuracy or time-saving figures are given. The results are the author's own description.

Try it in your business

What you'll need

Claude Code; sales and inventory data by SKU (the author pulled it from Amazon with scripts Claude Code wrote); written notes per brand covering supplier lead times, holiday closures, off-platform stock and past stockouts; an instruction file or command listing the projection steps.

Not disclosed: The scripts' code and how the Amazon credentials were connected; the full text of the instruction file and per-brand context files; the number of brands and SKUs; how accurate the projections turned out against actual sales.

Claude Code built custom scripts that pull data from Amazon with the author's credentials, plus a custom /inventory command; that is custom code rather than written instructions alone or an off-the-shelf app connection.

The original is a custom-built system. The prompt below is a simpler starting point and won’t reproduce it.

Author's example instructions

Author's example instructions · Alex Willen, The Automated Operator (Substack), 2026-01-29: the steps he lists for the /inventory command's instruction file

Published by the author as an example; not confirmed as the exact prompt behind the reported result.

1. Check to see if the sales/inventory data we have locally is >5 days old, and if not, pull fresh data from Amazon.
2. Check the context notes for the brand it's working on.
3. Pull inventory and sales data from the local cache.
4. Display the trailing twelve month sales data by SKU and by month.
5. Describe any factors it's going to use to make adjustments to TTM sales data when projecting NTM sales.
6. Review its stated adjustment factors, then project NTM sales by SKU on a monthly basis, and display the amount of stock remaining at the end of each month based on those projections. Use Python for the math here.
7. Recommend when to reorder each SKU, factoring in CNY and other holidays.

View in source ↗

Optional starting prompt (ours, untested)

How ours differs from the original setup: Same Claude Code execution agent. Works from an exported sales file and a written notes file instead of custom scripts pulling from Amazon; adds explicit check-ins before projecting and before applying adjustments, and keeps the output as a draft with no orders or supplier contact.

Our suggested starting prompt — not the author's original · untested
Read the sales and inventory export in [sales file] and my notes in [context file] (supplier lead times, holiday closures, stock held elsewhere, past stockouts). Before projecting anything, show me the trailing twelve months of sales by product and month, flag months that look unusually low or products with very little stock and nothing inbound, and ask me about them. Then list the adjustments you plan to make to last year's monthly sales and wait for my OK. Using Python for the math, project the next twelve months of sales by product and show the stock left at the end of each month. Finally, recommend a reorder date for each product, accounting for lead times and holiday closures, and show the numbers behind each date. Treat this as a draft for my review: don't place, send or change any orders, and don't contact suppliers.

Replace the [bracketed] parts with your own files and tools.

Get examples like this every Tuesday and Friday

Practical ways to put AI agents to work in your business. We check the original sources, explain the setup and point out the limits. Free.

Unsubscribe any time. Privacy policy

Report a correction

Related use cases

Build an estimate and job-cost tracker connected to QuickBooks, email and OneDrive

Have Grok Bot build an estimate and job-cost tracker connected to QuickBooks, email and OneDrive, as the author says he did to replace his construction-management software.

Grok Bot · Operations · Connected apps · Source: Pawan (@puvsandhu), owner of several companies; X bio: "Real estate. Property development. Construction." (surname not stated publicly) · November 6, 2026

Run a new client's standard audits and draft the kickoff strategy brief

Have Claude Code run a new client's standard first-week audits and draft a strategy brief with recommended priorities for you to review before the kickoff call.

Claude Code · Operations · Custom development · Source: Alejandro Arce, founder of Arce Consulting (Vancouver), writing about his own consultancy's client onboarding · June 16, 2026

Onboard a new client end to end: draft the contract, set up their Slack channel and podcast feed, and build website mockups for your review

Have Claude run a client-onboarding skill that drafts the client's contract, creates their shared Slack channel, adds them to your client database, and prepares samples, website mockups and a podcast feed for your review, while you send the invites, grant access and write the client messages yourself.

Claude · Operations · Connected apps · Source: Peter Hartree, who runs TYPE III AUDIO (T3A, bespoke AI narration services for the AI safety and effective altruism communities) and calls himself an AI Uplift Consultant; author of the AI Wow journal (wow.pjh.is); describing his own business's onboarding of the client Epoch AI · May 20, 2026