Input Specs
Input Specs
Start here when you need to know which CSVs to upload, which columns are expected, what values are valid, and where to download templates or working samples.
Product upload guides
Each page explains the current upload shape for a product, including required files, key columns, examples, common mistakes, and template or sample downloads.
SchedAI
Production
Use this guide to prepare the CSV files accepted by the SchedAI Production upload flow. The primary file changes with the selected environment, and optional helper files add job metadata, maintenance windows, or setup rules.
SchedAI
Service
SchedAI Service uses a multi-file routing bundle: technicians, locations, visits, and a required travel-time matrix, with an optional travel-distance matrix for distance reporting.
SchedAI
Employee
SchedAI Employee uses employees.csv and shifts.csv as the required scheduling inputs, with preferences.csv as an optional penalty layer.
SchedAI
Academic Scheduling
Use this guide to prepare CSV files for Academic Scheduling. The upload requirements depend on whether you are building a class timetable or an exam timetable.
LogiAI
CVRP
Use this guide to prepare the CSV accepted by the LogiAI CVRP upload flow. The workspace accepts the flat first-row-is-depot shape shown here, and exported scenario CSVs can also be re-imported.
Operational AI
Forecasting
Use this guide to prepare the CSV accepted by the Forecasting workspace. Every upload needs a timestamp column plus a numeric target column, and the workspace supports both single-variate uploads and multivariate uploads with additional numeric driver columns.
Operational AI
Anomaly Detection
Use this guide to prepare the CSV accepted by the Anomaly Detection workspace. The input shape depends on the detector you choose: univariate detectors require only a timestamp and y; the contextual detector requires at least one exogenous feature; and general multivariate detectors accept exogenous features as an optional enhancement.
Operational AI
Fraud Detection
Use this guide to prepare the CSV files accepted by the Fraud workspace. Training and scoring use different dataset roles: training builds the saved model version, while scoring evaluates new rows against the active model or a selected saved version.
Need another resource path?
Input specs work best alongside product and use-case pages
Use the input-spec pages for upload details, then move into public use cases or solution pages when you want workflow context or broader product guidance.
Navigate
Return to the resource hub
Move back to the full resources library when you want quickstarts, how-to guides, use cases, or policies instead.