From Idea to Production: AI Infra for Scaling LLM Apps

AI applications must adapt to new models, evolving workflows, and complex debugging challenges. This talk addresses the critical AI infrastructure needed to scale LLM applications from beta to production. It covers prompt management, data pipelines, Retrieval Augmented Generation (RAG), cost optimization, and GPU availability. Join Guy Eshet to explore strategies for building adaptability into LLM applications, focusing on addressing the challenges of building Generative AI and LLM apps, designing for adaptability, and preparing applications for future model advancements.