Results of the GRAU Data: AI-driven testing project (Video and Report, AMOS Summer 2025)
This project is one of the Scrum projects with industry partners that were part of the AMOS Summer 2025 Projects. Below please find the video (you may also like the other videos) and the project summary which details the final result of the project. We run these projects every semester, so please be in touch if you would like to motivate one of your own!
Demo Video
Project Summary
| Project name | AI Driven Testing |
| Project mission | Deliver a minimum viable product (MVP) of an AI-powered test generation assistant that interacts effectively with real-world software projects. This includes laying the empirical and research groundwork for the idea. From this research we will conclude a MVP, that can analyze simple Python and C++ programs and produce corresponding test cases. Operated through a user-friendly chat interface. The MVP will showcase initial integration with widely used open-source testing frameworks such as Robot Framework, proving the viability of AI-assisted test automation in practical, everyday development environments. |
| Industry partner | GRAU DATA GmbH |
| Team logo |  |
| Project summary | We had the great opportunity to get hands on experience partaking in AI driven agile software project developing an LLM based solution for generating tests. Furthermore we incorporated university grade research to validate our implementation using industry standard methods. Our core finding is that the quality of the LLM Response is not necessarily correlated to the parameter size. Beyond that our essential find lays in the comprehensive wiki documentation https://github.com/amosproj/amos2025ss04-ai-driven-testing/wiki. |
| Project illustration | N/A |
| Team photo | N/A |
| Project repository | https://github.com/amosproj/amos2025ss04-ai-driven-testing |
| Additional information | N/A |