Inventory & Reorder Analyst
What to reorder, what to stop buying, and what it is assuming
- 7hard rules
- Things it must never do, enforced in every run
- 5handover rules
- Conditions where it stops and gives the work to a person
- 8output fields
- A structured result, not a paragraph you have to re-read
- ≤5steps per run
- Bounded work: at most 4 tool calls, enforced by the runtime
Read-only by design. This agent has no path to sending, spending, publishing or committing anything. Where that limit is the product, removing it would remove the reason to trust the output.
Overview
Two things quietly kill a small retailer: running out of the lines that sell, and burying cash in the lines that do not. Both are arithmetic, and both get done badly because doing them properly means maintaining a spreadsheet nobody maintains.
This agent does that arithmetic on your own data. For each line: how fast it is selling, how many weeks of cover you hold, when to reorder given the supplier's lead time, and how much cash is sitting in stock that has not moved.
What makes it usable is what it refuses to do. It states the assumptions behind every number, and it says plainly when your history is too short or too erratic to support a recommendation — with eight weeks of data there is no seasonality to find, and a confident reorder quantity built on that is how a shop ends up holding a year of stock. It never places an order, and never contacts a supplier.
Benefits
Stop selling out of your best lines
The stock-outs that cost most are the predictable ones.
Free the cash
See exactly which stock is holding your working capital.
Numbers you can challenge
Assumptions stated, so you can correct them.
What it does
Cover and reorder points
Weeks of stock remaining and when to reorder, using each supplier's actual lead time.
Finds the cash you have buried
Lines that have not moved, with the money sitting in them.
States its assumptions
Every number says what it assumed. A figure whose basis is hidden cannot be argued with.
Admits when it cannot tell
Too little history, or demand too erratic, is reported as low confidence — not smoothed into a recommendation.
Flags the lines about to hurt
What will stock out before a reorder could arrive, ranked by what it costs you.
Orders nothing
No purchase orders, no supplier contact. It produces the analysis.
What this changes
What this changes about your week
- It takes over
- The reorder spreadsheet nobody maintains.
- Done today by
- The owner, from memory.
- How often
- Weekly buying decisions.
- Typical manual effort
- Cover and reorder points across a real catalogue is a day.
Why Retail in particular. It states its confidence and says when your history is too short. A confident reorder quantity built on twelve weeks is how a shop ends up holding a year of stock.
Runs unattended
Started by you or by an event, and it finishes on its own. Nothing waits for someone to be at a desk.
The same standard every time
The two-hundredth item is held to the bar the first one was. Consistency is the part people cannot sustain.
It cannot act on its own
Inventory & Reorder Analyst has no path to sending, spending or committing. That limit is why its output is safe to act on.
How it runs
This agent runs server-side through the PROMIVO runtime. Each run is logged step by step and every tool call is permission-checked before it executes.
- 1InputValidated against the agent input schema
- 2Modelclaude-sonnet-5 with automatic fallback
- 3Toolsextract_structured_data
- 4PermissionsRuns READ actions automatically; anything higher waits for approval
- 5OutputStructured result matching the output schema
- 6LoggingTokens, duration and every step recorded
Demo
Demo dataIllustrative sample output, abridged.
Input
{
"currency": "EUR",
"products": [
{
"sku": "BAG-38",
"name": "Canvas bag",
"unitsSold": 96,
"stockOnHand": 14,
"leadTimeDays": 21
}
],
"periodWeeks": 12
}Output
{
"reorder": [
{
"sku": "BAG-38",
"basis": "8 units/week over 12 weeks. 12 weeks cannot show seasonality, so this assumes demand holds.",
"reorderBy": "immediately",
"confidence": "medium",
"weeksOfCover": 1.75,
"suggestedQuantity": 96
}
],
"escalate": true,
"deadStock": [],
"disclaimer": "Figures from your own sales and lead times, each with its confidence and the assumptions behind it. No purchase order has been drafted or placed and no supplier has been contacted.",
"assumptions": [
"Velocity from 12 weeks of sales; returns not excluded because none were supplied.",
"Lead time 21 days as supplied."
],
"cannotAssess": [],
"stockOutRisk": [
{
"sku": "BAG-38",
"daysUntilOut": 12,
"revenueAtRisk": 720
}
],
"escalationReason": "BAG-38 will stock out roughly 9 days before a reorder could arrive."
}Requirements
Integrations
No integrations required.
Before you start
- Sales history per product
- Current stock levels
- Supplier lead times, where known
- Requires the Starter plan or higher
Use cases
Weekly buying decisions
What to order this week, and how much.
Before a peak season
What will run out, and what to order now.
A cash squeeze
Find the stock that has stopped earning its shelf space.
Pricing
Starter
Billed monthly through your PROMIVO subscription. Cancel at any time.
Runs consume your plan allowance for agent executions and tokens. See plan limits
FAQ
Can it place orders?
No, and it cannot contact a supplier. Spending money is not something an agent should do on its own, and a wrong quantity is expensive in a way a wrong report is not.
How much history does it need?
It works with what you have and says how confident that makes it. Under about twelve weeks it will tell you the recommendation is directional, and it will not claim to see seasonality that short a history cannot show.
Does it handle seasonal products?
Only where your history actually covers the season. Otherwise it says so rather than assuming last month repeats.
Reviews
Reviews open once customers have run this agent.
Need this agent to work differently?
Tell us what to change and our team will scope a customised version for your business.
Customize this agent