Experiments

Track experiments to try out new features and resolve existing issues

You can generate runs of your Atla Insights experiments by using the run_experiment context manager.

from atla_insights import run_experiment

with run_experiment(
    experiment_name="my-experiment-name",  # optional: defaults to random identifier
    description="Testing out shiny new feature",  # optional
):
    # Your experiment code here

Inside the context manager, you can run your instrumented agent code as usual.

As a result, you will be able to see granular and semantically rich insights about your experiment.