Analyze results

AI-driven analysis of recorded desktop data in Unassisted Task Mining to identify automation candidates.

Once you’ve completed recording variations of your task, it’s time to leverage AI.

Unassisted Task Mining is integrated with UiPath® AI Center™ to run the machine learning model and analyze the dataset.

The datasets you upload should contain at least 10,000 actions, but we recommend 50K actions as a good baseline. The model can support up to 200K actions collected in a project. As a quick way of estimating, an active user typically provides 200-1K actions per hour, depending on the scenario they are recording.

After running the machine learning model integrated from AI Center™, you'll see task discovery results in your Unassisted Task Mining Project. These results are determined by collected all the recorded actions and screenshots and leveraging AI to determine discrete steps and their repeatability.

Once the model has determined the discrete steps that are frequently repeated, it will create tasks to group together those steps into visualizations.

Reviewing the presented tasks, traces and trends will provide additional insight into your organization and process. You can follow our Unassisted Task Mining Analysis Guide after you’ve run the machine learning model (see steps in the next subsection) to leverage best practices to drive continuous discovery and actionability from your project.