This podcast episode, titled "Deep Dive," focuses on generative AI agents, specifically dissecting a paper from February 2025 titled "Agents." The hosts break down the core concepts of AI agents, explaining their components: the model (language model), tools (extensions, functions, and data stores), and the orchestration layer. They discuss how these agents differ from standalone AI models, emphasizing their ability to learn, retain information, and interact with the external world. The hosts also explore cognitive architectures like REACT, Chain of Thought, and Tree of Thoughts, and delve into practical applications using LangChain and Vertex AI agents, aiming to provide listeners with actionable insights for projects and innovations in the field.
Sign in to continue reading, translating and more.
Continue
