diff --git a/docs/quick_start.rst b/docs/quick_start.rst
index 8f4e78f..b240dcb 100644
--- a/docs/quick_start.rst
+++ b/docs/quick_start.rst
@@ -15,3 +15,13 @@ For quick start, please see the examples of launching an active learning annotat
 +-----+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
 | 3   | `Benchmarking a novel AL query strategy / unlabeled pool subsampling strategy <https://github.com/AIRI-Institute/al_toolbox/blob/main/examples/benchmark_custom_strategy.ipynb>`_ |
 +-----+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+
+By default all outputs save in the folder: acleto/jupyterlab_demo/output/dataset_name
+
+- checkpoint_{num_itration} - folder with saved model on each iteration of active learning
+- annotation.json - annotated data
+
+If you don't want to save model on each iteration of active learning you need to
+add a field al.save_checkpoints = False in the config file. All using configs locate in the current path: acleto/jupyterlab_demo/configs
+
+For more information check :ref:`config_structure`
\ No newline at end of file