Sydney Runkle

Sydney Runkle, an open-source developer at LangChain, dives into the world of agentic AI workflows using LangGraph. She explains how integrating agentic frameworks can supercharge Python applications with large language models (LLMs). The discussion highlights the balance of AI-driven workflows, transparency in software development, and the importance of context and memory in enhancing user interactions. Runkle also shares insights on developing intelligent agents and managing application interrupts, showcasing practical examples that bridge creativity with responsibility in AI.

Sydney Runkle, a LangChain developer who builds open source agent tooling, walks through Deep Agents and how they make models plan, iterate, and recover. She discusses planning and to-do systems, file system context, sub-agents and parallel work, middleware hooks, MCP interoperability, and using any model or local runtimes. Practical demos, CLIs, and safety sandboxes round out the conversation.

Sydney Runkle shares Pydantic performance tips to optimize code efficiency, covering techniques like using tag unions for discrimination in validation, efficient creation of type adapters, and strategies for importing code specifications. The discussion also explores discriminators for nested models, 'skip validation' annotations, and tools like CODSPEED for benchmark tests. Learn about Pydantic's impact on projects like FastAPI and the potential integration with large language models for enhanced productivity.