Skip to main content
An experiment is where you train predictive models. You give it a dataset and a target property, choose a mode, and Chemolytic produces trained models you can deploy.

Hierarchy: experiment, job, trial

Three concepts, nested: You don’t usually think about jobs in CoPilot mode. The hierarchy matters most in Scientist mode, where you create jobs one at a time.

Regression vs classification

The type of your target property determines whether the experiment is a regression or a classification problem. You don’t choose this manually. This affects:
  • Which algorithms are available
  • Which metrics are reported
  • How results are visualized

CoPilot vs Scientist

Two modes for building models, set when you create the experiment. You can’t switch modes after creation. If you change your mind, create a new experiment.

Experiments page

Go to Experiments in the project sidebar.
Experiments list page showing name, target property, dataset, mode, status, best model, and CV score

Filters

The list polls every 3 seconds when any experiment is running, so progress updates live.

Status badges

Plan limits

Two monthly quotas, shown at the top of the Experiments page: Both reset at the start of your billing period. The widget shows when the next reset happens. If you hit a quota mid-month, you can still browse and inspect existing experiments; only creating new ones is blocked.

Deleting an experiment

Click the trash icon on a row, or the Delete action in the detail page.
Deleting an experiment removes all its jobs and trials permanently. Models that were registered from those trials still work (they have their own copies), but the trial details cannot be recovered.

What’s next