Engineering teams often feel stuck not knowing how to even start building "GenAI applications." In this workshop, we will introduce a repeatable development workflow for architecting and building GenAI applications, which will help you avoid introducing unnecessary complications and error-prone abstractions. Attendees will get hands-on with some of the latest GenAI models (like Llama 3.1) to learn about basic prompting, prompt engineering, chaining, augmentation, and more. Leaving the workshop, engineers and technologists will feel confident enough in these skills to recognize appropriate opportunities for AI in their businesses and "smell test" solutions that promise too much, are overly complicated, or underutilize AI's capabilities.
Speaker
Daniel Whitenack
Founder & Data Scientist @Prediction Guard, Co-Host of the Practical AI podcast, Previously Built Data Teams at Two Startups and an International NGO
Daniel Whitenack (aka Data Dan) is a Ph.D. trained data scientist and founder of Prediction Guard. He has more than twelve years of experience developing and deploying machine learning models at scale, and he has built data teams at two startups and an international NGO with 4000+ staff. Daniel co-hosts the Practical AI podcast, has spoken at conferences around the world (QCon, ODSC, Applied Machine Learning Days, O’Reilly AI, GopherCon, KubeCon, and more), and occasionally teaches data science/analytics at Purdue University.
beginner to intermediate
