Kirelta Decisions API
Walkthrough

Watch one model lose your trust — and earn it back

This runs against the real engine. It trains a baseline, then feeds it four batches: one healthy, one slightly off, one badly drifted, and one that comes back. The input is a fixed, verified dataset — the same one every time, so the four outcomes are the same for everyone.

Uses a model called demo in your tenant. Safe to run again. No key? Get one free.