Docs/jAIn

jAIn

From a spreadsheet to a model.

One session takes a CSV and gives back a trained model, a report explaining it, and predictions. Nothing to install and no notebook to write.

What a session looks like

  1. Sign in with a magic link or a password.
  2. Upload a CSV or TSV and say what you want predicted.
  3. The run is queued. One session runs at a time per account.
  4. A container starts on an isolated network and does the work.
  5. Results are captured before the container stops, so they stay readable afterwards.

What you get back

A trained model, a report describing how it was found and how well it does, and predictions for the rows you asked about. All three are downloadable for as long as they are kept.

How long results are kept

Uploaded data and everything produced from it are deleted automatically after 30 days. You can delete a session, or your whole account and all of its data, at any point before that. The details are on the privacy page.

This number is not written by hand — it comes from the same configured value the app enforces, so the promise on this page cannot drift away from the deletion that actually runs.

Running it yourself

The hosted service runs the same appliance image you can download and run on your own hardware, with no network access at all. The product page covers that, and the security review covers what isolates a hosted run.