Sam Partee, CTO of Arcade AI, explains that building production-grade agentic systems requires moving beyond simple chatbots. He details the critical components for creating reliable, secure, and scalable tools, including rigorous schema management, the principle of least privilege, continuous evaluation, and a crucial distinction between 'exploratory' and 'operational' tools.
Drawing surprising parallels between AI agents and robotics, this talk argues that the agent development community is repeating a key mistake from the self-driving industry: underestimating the difficulty of action and over-focusing on reasoning. It covers essential robotics concepts like DAgger, MDPs, simulation, and the critical importance of a robust offline infrastructure, explaining why perfect reasoning doesn't guarantee successful execution in the real world.
Robin Bordoli of Weights & Biases explores AI's exponential growth, from past achievements to the current agentic landscape. He discusses the rise of reinforcement learning, the challenge of productionizing reliable agents, and highlights how foundational issues in AI development persist even as model capabilities soar.
Zhen Lu, CEO of Runpod, discusses the shift from Web 2.0 architectures to an "AI-first" cloud. The conversation covers the unique hardware and software requirements for production AI, key use cases like generative media and enterprise agents, and the critical challenges of reliability and operationalization in the new AI stack.
Jerry from LlamaIndex explains why naive Retrieval-Augmented Generation (RAG) fails in production and dives deep into advanced data quality techniques—from parsing complex documents and hierarchical indexing to chunking best practices—required to build robust, high-quality LLM applications.
Jay Alammar, Director at Cohere, discusses the practical adoption of Large Language Models in the enterprise. He covers the evolution of Retrieval-Augmented Generation (RAG) from a simple anti-hallucination tool to complex, agentic systems, the critical role of evaluation as intellectual property, and future trends like text diffusion and the increasing capability of smaller models for specialized business tasks.