Alex Strick van Linschoten, a machine learning engineer at ZenML, joins the MLOps Community podcast to discuss his comprehensive database of real-world LLM use cases. Drawing inspiration from Evidently AI, Alex created the database to organize fragmented information on LLM usage, covering everything from common chatbot implementations to innovative applications across sectors. They discuss the technical challenges and successes in deploying LLMs, emphasizing the importance of foundational MLOps practices. The episode concludes with a call for community contributions to further enrich the database and collective knowledge of LLM applications.

AI Agents as Neuro-Symbolic Systems: Expanding the Boundaries of Intelligence" The current discourse around AI agents often centers on LLM-based systems with tool-calling capabilities, like REACT agents. While effective, this narrow definition limits the potential of agents to solve complex, real-world problems. In this talk, we explore a broader, more robust perspective—AI agents as neuro-symbolic systems. By combining neural networks' adaptability with the precision of symbolic reasoning, neuro-symbolic architectures bridge traditional AI approaches and modern advancements, enabling scalable and versatile workflows. This expanded definition accommodates not only LLMs but also embedding models, decision trees, and hybrid systems that integrate various modalities of intelligence. We will delve into: 1. The evolution of AI agents and the limitations of current models. 2. The core principles of neuro-symbolic systems and their practical applications. 3. A reimagined framework for building intelligent agents that operate flexibly across diverse tasks. This session aims to redefine the way we think about AI agents, empowering developers and researchers to design systems that are more efficient, resilient, and capable of tackling dynamic challenges. Join us as we explore the future of agentic AI and its transformative potential.