Abstract
Software development includes writing tests and executing the tests to ensure that the software application works as intended. However, manually written tests are expensive, time-consuming, and can often be incomplete and/or may not be available. This disclosure describes the use of a large language model (LLM) to automatically generate test scenarios for the most common paths that real users take when using an application. Data regarding such common paths is available for many applications since application owners have a need to view analytics on which portions of their application are visited and the user engagement with different portions of the applications. Such data can be obtained automatically (with appropriate user permissions) from an application that is instrumented to generate application telemetry such as application events, page transitions, etc. A large language model is provided with a prompt that includes a description of the application, recordings of the user interface of the application, and page transitions obtained from the telemetry. The LLM generates valid user journeys through the application and specifies tests for the different user journeys.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Velusamy, Siva, "Automatically Generating High Value Tests for User Journeys of an Application", Technical Disclosure Commons, (October 24, 2025)
https://www.tdcommons.org/dpubs_series/8782