An agent that combines sales velocity, seasonality, and supplier lead times to draft purchase orders before you run out — and flags the dead stock tying up your cash.
Units per day per SKU across channels, from live listings and recent sales — not last quarter's spreadsheet.
2
Add lead time + buffer
Each supplier's real lead time, plus your buffer, turns velocity into a reorder date per SKU.
3
Draft the PO
Quantities rounded to case packs and MOQs, supplier-ready. You approve; it doesn't order.
4
Flag dead stock
SKUs with 90+ days of cover get listed with the cash they represent — clearance candidates, priced for your call.
5
Weekly rhythm
A Monday report: order this week, watch list, dead-stock list. No daily noise.
What it needs
Inputs & tools
Sales velocityLive data (FreshCrawl)
SuppliersLead times, MOQs
Case packsPer SKU
OutputDraft POs weekly
OrderingHuman-approved
Your time≈ 30 min/week
Stock-outs usually aren't forecasting failures — they're arithmetic nobody redoes weekly. Velocity × lead time is simple math; the agent just never forgets to run it, for every SKU, every week.
Run this agent yourself
⚡
1 · Get a FreshCrawl subscription
The agent runs on live marketplace data. FreshCrawl plans start free (1,000 credits), paid plans from $29/mo — every plan includes MCP access and an API key. freshcrawl.io →
🔗
2 · Link the MCP to your LLM
In Claude or ChatGPT, add a custom FreshCrawl MCP connector — server crawl.onewally.com/mcp — and paste your FreshCrawl API key. Your LLM can now pull live offers, Buy Box history, and sales estimates itself.
📋
3 · Paste the prompt
Copy the prompt below into your LLM and name your store. The agent runs against the live data it can now reach — no code, no exports.
Copy the prompt
Starter prompt
Step 3 · Paste this into your LLM
# Reorder Forecast
Use the FreshCrawl MCP connected to this chat for all live marketplace data.
MY STORE (fill in once):
- Store name: [your store name]
- Seller ID or storefront URL: [paste it — the agent uses it to find your catalog]
- Marketplace: [Walmart US / Amazon US]
First, use the FreshCrawl MCP to look up my store, pull my catalog,
and work only on my listings. If you can't identify my store from
what I gave you, ask me for my storefront URL before anything else.
RUN SCHEDULE (set this where you run the prompt):
- Run this prompt: weekly, Mondays at 6:30 AM.
- If your LLM app supports scheduled/recurring tasks, set it there; otherwise re-paste the prompt on that cadence.
For each SKU, compute units/day from the last 30 days of sales.
Using each supplier's lead time plus a 7-day buffer, list SKUs
that will stock out before a new order could arrive. Draft POs
with case-pack rounding and MOQs. Separately, list SKUs with over
90 days of cover and the cash tied up in each. Weekly, Mondays.
EXECUTION — READ CAREFULLY:
You draft purchase orders. I place every order myself — you have no supplier or payment access.
The prompt gets you the shape. The reliable version runs on live data through the MCP — that's steps 1 and 2 above.
Clusters return comments to find the few fixable causes behind most returns.
Questions sellers ask
Does it place orders?
No — it drafts POs for your approval. Money leaving the business is a human decision.
What about seasonal spikes?
Velocity windows include the same period last year when data exists; flagged SKUs show both the 30-day and seasonal rate so you can judge.
Multi-channel inventory?
Velocity is summed across channels per SKU; if your counts live in a sheet or system, that's the input it reads.
Run this on your store.
Every agent here runs on live FreshCrawl data through the MCP. Start free, connect your LLM, paste the prompt — or get the free Buy Box Loss Report and see the data first.