GenAI Cracow #12

Abstracts

​GenAI Test automation & execution

Fernando will show a solution his team has been working on, that combines electronics, Arduino, Python, C#, Computer Vision, and Google Generative AI. The system to capture images of applications on any touch screen device and identify all interactive elements. In the next stages they are using Google Gemini API, to generate Selenium test cases, which are executed by the robotic tester.

​Multimodal content generation

We can see that many people generate social media posts using Generative AI. One could say, that too many people. Let's spice it up, and generate also videos and music. Sounds boring? Okay, but what if I told you that you won't need for this another subscriptions and you can do it via one API?

​Speakers

​Fernando Mileski

Fernando holds a degree in Systems Analysis from UNIP São Paulo and brings over 22 years of experience in Quality Assurance Analysis (QAA) and Software Development Engineer in Test (SDET). Before joining GlobalLogic, Fernando worked with various tech giants such as General Motors, IBM, and Ericsson. Over the past 7 years, he specializes in innovations for the industrial instruments automation sector

​​Konrad Bujak

Generative AI Engineer and Product Manager, working in IT for the past 12 years. MSc. in AI Engineering. Co-founder and CTO @ BuyerMind (data mining company). Sometimes also a private consultant helping companies implementing Generative AI features / products and building product (engineering) teams. IoT and homelab enthusiast.