Manually Training the UP9 Model

UP9 has several modes of operations. It can be deployed 'close' to each service (e.g. as a sidecar in Kubernetes), however, it can also be used to record workflows and automatically create tests to cover those workflows.

Once you have the UP9 CLI installed, you are ready to start recording workflows using Google's Puppeteer.

Launch Puppeteer

The following command will open up a browser window and will record session traffic into a new or an existing Workspace. From your terminal, run:

Copy to clipboard
up9 tap:start

'' is the name of your new workspace, so you may want to choose something more descriptive, or if you'd like to add workflows to an existing workspace, use the name of an existing workspace.

This command will open a new Chromium browser window. Use this browser window to go through the Workflow you'd like to record. All steps made in this browser will be recorded and sent for processing.

Browser Window

Allow Chromium permissions when prompted. As you browse, you will see a requests counter (in separate tab) incrementing, which indicates application traffic is being recorded and sent for processing.

When done, close the Chromium browser and view your workspace in the UP9 dashboard. You can learn more about UP9's dashboard in the Observability page.

Model Accuracy

UP9 uses machine learning to create a model that is based on recorded traffic, so record the same workflow several times into the same workspace to increase the model's accuracy. The more passes performed, the stronger the confidence level of the model.


For support, feel free to use any one of the three: