Plan inventory per product. Upload 18 months of sales, add holiday and promo dates. Forecast predicts the next twelve weeks of demand for every product, with a range, not a guess.
Forecast
Predict what's coming: sales next quarter, the inventory you'll need, cash flow, customer volume. Upload your past numbers, pick what to predict, and get a clear forecast with a confidence range. No spreadsheet formulas, no data-science team.
Try ForecastGoogle TimesFM 2.5, not hand-tuned.
No ARIMA tuning, no LSTM wrangling: it generalises across any series with enough history to be useful out of the box.
A node per transformation.
Confidence, not a point.
Holidays, promos, weather.
Fork, tweak, compare.
Every run is a record. Change the preprocessing, rerun, compare accuracy over holdout windows.
Your planning shouldn't live in one person's spreadsheet.
Forecast is the execution layer between your history and your next decision. Point it at a CSV, a database or your CRM, pick what you want to predict, and it returns a forecast with a band you can actually plan around.
Use Cases
Real scenarios teams ship with Forecast. Same agent, plugged into a workflow they already care about.
Catch cancellations early. Forecast learns your normal revenue and cancellation pattern, then pings you the moment the numbers start drifting.
Forecast revenue and cash. Pulls invoicing data, cleans out the seasonal bumps, and writes a rolling six-month revenue forecast by service line.
Staff the right shift. Predicts how many customers each location sees, hour by hour, factoring in weather, local events and season. That drives the schedule.
Staff the right shift. Predicts how many customers each location sees, hour by hour, factoring in weather, local events and season. That drives the schedule.
Integrations
Every pipeline is yours to fork, tweak and schedule. Start from a template or wire your own nodes: the runtime does the rest.