Plan further ahead
19% lowerforecast error
See six months ahead.
Lower error than using last month’s sales to forecast six months ahead.
Spark InventoryWhat should I order now?
Purchasing with Demand ESP
What should I order now?
Get a reorder recommendation you can review.
Demand ESP forecasts each item from your sales history. Spark Inventory combines that forecast with supplier lead times and, as order history builds, how much they vary to set reorder points, then proposes draft purchase orders for your team to review. Receipt variances and supplier price books live in the same system, so you or your assistant can check them before you approve.
Onboard with Sparki in app or your own AI assistant over MCP.
What your team gets
Purchase Order Management
Create, track, and manage purchase orders from request to receipt. Automated PO numbering and approval workflows.
Supplier Management
Maintain detailed supplier records with contact info, payment terms, lead times, and performance history.
Delivery Receipts & Receiving
Streamlined goods receiving with barcode scanning. Partial receipts, quality checks, and automatic inventory updates.
Request for Proposals (RFP)
Send RFPs to multiple suppliers and compare quotes. Track responses and select the best pricing.
How a recommendation is built
From forecast to a draft PO you approve
A daily reorder sweep, on by default, rechecks stock against reorder points and proposes draft POs for review. Change its schedule or turn it off any time.
- 01
Demand forecast
Demand ESP forecasts each item from your sales history.
- 02
Lead times and their variability
Supplier lead times, and as order history builds, how much they vary.
- 03
Reorder point
Forecast and lead times set when each item needs to be reordered.
- 04
Proposed draft PO
Spark Inventory proposes a draft purchase order with the reasoning attached.
- 05
Your review
Your team checks it, adjusts it, and approves it.
Check before you approve. Receipt variances and supplier price books live in the same system, so you or your assistant can look at them as you review the draft.
Measured lead times. For an item with enough qualifying purchase history, Spark Inventory can use measured lead times and their variability instead of supplier defaults.
Put inventory to work
12% lessstock held
Hold less. Keep orders moving.
Less inventory than last-month forecasting, at the same 98% fill rate.
Get value sooner
Under 1hour to forecast
Bring your files. Start planning.
From export files to a working forecast with Sparki or your own AI assistant.
Powered by Demand ESP
Every SKU. Its own forecast.
Demand ESP reads each item’s demand pattern and automatically selects a forecasting method. See the method chosen and the history behind your forecast.
Forecast and inventory results from public-data testing.
How we measured it
The 19% and 12% figures were measured in September 2026 on an earlier version of our forecasting engine.
A method for each demand pattern
Demand ESP selects statistical methods for steady, trending, seasonal, and intermittent demand, using the available sales history and fallbacks for limited data.
What the 12% measures
In an inventory simulation using 400 Iowa public-data items, average on-hand inventory cost was approximately $4.12M for Spark Inventory versus $4.67M for last-month forecasting at an interpolated 98% fill rate. Both used the same order-up-to policy, a 14-day lead time, lost sales, and a uniform $12 unit cost.
What the 19% measures
Retrospective testing on 799 Iowa items found six-month pooled weighted absolute percentage error (WAPE) of 22.0% for Spark Inventory versus 27.1% for last-month forecasting, a relative reduction of approximately 19%.
What onboarding time measures
Measured from customer export files to a working forecast. Setup time varies with data readiness and scope.
Promotions and demand events
Plan the promo, see what it needs, then review how it went
A forecast that reacts to your business, not only to past sales. The Demand Calendar in Demand ESP holds the campaigns, discounts, email and SMS sends, price changes, launches and wholesale orders that move demand. Once you add an event to the forecast, purchasing suggestions include it.
- 01
Plan the promo
Add an event with its dates, products and offer, or confirm one Spark found in your connected tools. Spark suggests the expected effect as a likely range, and the event joins the forecast when you add it. Drafts don’t change the forecast or purchasing.
- 02
See what it needs
Each event gets a stock check. If a product runs out before the event ends, you see what is on hand, what is needed, when it runs out, and an order-by date based on the supplier’s usual lead time.
- 03
Review how it went
When the event ends, compare what you expected with what happened. The result goes into the track record for that event type, so the next suggestion for it starts from what you learned.
What’s affecting demand
5 events coming up1 Campaign1 Email & SMS send1 Discount or sale1 Product launch1 Wholesale order2 need review
CalendarListTo review 2Track record
- 1event found in Shopify
- 1event where stock runs out
- 1event ended: compare with what you expected
OctNovDec
Campaign
Holiday gift guide
Email & SMS send
VIP early access
Discount or sale
Fall tee saleStock risk
Price change
Product launch
Canvas Tote, Black
Wholesale order
Harbor Goods order
Suggested, not in the forecast yetDraftIn the forecast
Stock runs out before this event ends
Fall tee sale · 1 product runs out, the first around Oct 21.
- On hand
- 42
- Needed
- 96
- Runs out
- Oct 21
Classic Tee, Black, M
Order 60 by Oct 12Expected 20%, got 17%
Summer tee sale · Ended Aug 31 · Discount or sale
What Spark learned
Your Discount or sale events came in 3 points under the expectation. Future suggestions for this type now start a little lower.
Slow mover markdown
Markdown proposals for what isn’t selling
When an item has stock but no recent sales, Spark can propose a markdown in Spark Signal. You set the price and see what waiting costs. The item price does not change until you approve it.
Dad Cap, Olive
What waiting costs
- Capital tied up
- $1,240
- Units on hand
- 124
Set the price
Markdown price$16.00
27% below the current price.
Create markdown proposalDismiss
See the full workflow
From demand signal to reviewed draft PO
Watch a three minute walkthrough using real Spark Inventory screens and clearly labeled example data.
Complete capability
Everything you need to run purchasing
Built into the same system that tracks stock, orders, purchasing, warehouses, and the decisions between them.
Purchase Order Management
Create, track, and manage purchase orders from request to receipt. Automated PO numbering and approval workflows.
Supplier Management
Maintain detailed supplier records with contact info, payment terms, lead times, and performance history.
Delivery Receipts & Receiving
Streamlined goods receiving with barcode scanning. Partial receipts, quality checks, and automatic inventory updates.
Request for Proposals (RFP)
Send RFPs to multiple suppliers and compare quotes. Track responses and select the best pricing.
Supplier Return Orders
Process returns to suppliers for defective or incorrect items. Track return shipments and credits.
Reorder Point Planning
Set minimum stock levels and automatically generate purchase suggestions when inventory runs low.
Backorder Management
Track items on backorder and automatically allocate incoming stock to waiting orders.
Demand ESP reorder planning
Each SKU gets its own forecast method. Review the forecast, recommended quantity, and timing before a draft PO is created.
Landed Cost Calculation
Calculate true item costs including shipping, duties, and fees. Allocate costs across purchase order items.
From signal to action
A decision workflow your whole team can follow
01
Ask the onboarding agent
Use Sparki in app or your own AI assistant over MCP to inspect what exists and bring in the data your team already trusts.
02
See the recommendation
Spark Inventory turns sales, stock, and lead times into a clear next action with the reasoning attached.
03
Approve and move
Review, adjust, and approve in one place. Your team keeps control without rebuilding the analysis every week.
See your own inventory plan in Spark Inventory
Upload the data you already have and turn it into the next decisions your team needs to make.
Ready to upgrade your purchasing process from Fishbowl or spreadsheets? See how the move works.