AI Inventory Forecasting
Predicts tomorrow's prep list from your sales, schedule, and weather.
Model version: inventory-forecast-v1.2
Methodology contact: Head of Data Science
Start free trial — no credit card
ROI
Pilot in progress
N=23 trucks, started 2026-01-15, readout expected 2026-06-30. We will not publish a number until we have one.
What it does
Reads historical POS sales, published TruckSchedule, local weather forecast, and day-of-week patterns. Outputs a per-SKU prep recommendation for the next service window — how many proteins to thaw, how many tortillas to press, how much produce to prep. Operator confirms and adjusts before prep starts.
Who it is for
- Single Truck
- Small Fleet
Integrations
What this feature doesn't do
- Forecasts degrade in the first 30 days while the model learns the truck patterns.
- Major weather events need operator override.
- New menu items have no history and revert to a category-average estimate.
- The forecast is a recommendation; the operator still walks the cooler.
Pricing
Included with Operator Pro.
See all plansFAQ
- How long does AI Inventory Forecasting take to learn my truck?
- Roughly 30 days. The model needs to see a full cycle of weekdays, weekends, and weather patterns before its recommendations stabilize.
- What does AI Inventory Forecasting cost?
- Pricing is transparent on the pricing page. Most features are included with Operator Pro. There is no demo gate on headline price.
- Is the model version pinned?
- Yes. AI Inventory Forecasting runs on model version inventory-forecast-v1.2. We disclose this on every page and in JSON-LD softwareVersion.
- What integrations does it require?
- Required integrations: square, toast, clover, noaa-weather.
- What does this feature not do?
- Honest caveats: Forecasts degrade in the first 30 days while the model learns the truck patterns. Major weather events need operator override.