Problem Statement:
A company operating in a global networking product solution wanted to build and improve the Test Automation for the legacy network management solution to reduce the time to market and make sure that the product or its components fit predefined standards of quality in terms of functionality, and interaction with the user. The opportunity was to improve the framework to auto heal, recover and adapt to application changes using Artificial Intelligence.
Solution Overview:
The solution was to create a Machine Learning model by giving training data taken from actual Test automation failures or application related changes causing failures. The model was created for any existing test automation framework to be able to integrate seamlessly using LLM and auto heal or recover from failures related to changes in application.
Benefits Delivered:
The model was initially deployed with a moderate number of frequently seen problems. It was received well by the users as it saved them several minutes of automation scripts rectification and fixes. Efficiency improved and with few/absolute no monitoring of test executions.
