How it works
Two paths, then one API
Bring tables for ML and Forecast, or start with no dataset for Loop and Resolve. Both end in a monitored endpoint.
ML
Churn classifier
gold.customers
Forecast
Demand plan
gold.orders
Platform architecture
Two paths. One API.
ML and Forecast train on gold from Lake and Lab. Loop and Resolve start with no dataset. Both ship a monitored endpoint.
From your data
Data Warehouse → ML and Forecast
Ingest and explore in Lake and Lab, publish gold, then train classification, regression, or a time series. These products need your tables.
Lake layers
Production
Deploy and monitor
Either path ends in a REST API, usage monitoring, and a health check. The key is issued on the asset, then your app calls it.
Already have a database? Connect a database in Lake · Create a Free Account
Products
Bring data, or start without it
Data Warehouse, ML, and Forecast train on the tables you publish. Loop and Resolve start with no dataset.
Needs your data
Starts with no dataset
Applied intelligence
Problems like the ones on your desk
Ready to put a model in production?
Bring data, or start without it.
ML and Forecast train on gold from Lake and Lab. Loop and Resolve start with no dataset, including ticket routing and urgency scoring.