Thomas Prexl
Thomas is an expert in tech transfer and startup development, with a career focused on fostering innovation and bridging the gap between research and industry. He has led initiatives like accelerator programs, innovation networks, and hackathons. A Generative AI enthusiast and co-founder of neunzehn innovations, Thomas helps companies leverage AI technologies. He holds a doctorate from the University of Basel and is a dedicated advisor, educator, and speaker in the startup ecosystem.
Session
Demos and prototypes for generative AI (GenAI) projects can be quickly created with tools like Streamlit, offering impressive results for users within hours. However, scaling these solutions from prototypes to robust systems introduces significant challenges. As user demand grows, hacks and workarounds in tools like Streamlit lead to unreliability and debugging frustrations. This talk explores the journey of overcoming these obstacles, evolving to a stable tech stack with Qdrant, Postgres, Litellm, FastAPI, and Streamlit. Aimed at beginners in GenAI, it highlights key lessons.