LLMs in Prod w/ Exa & Portkey

​AI adoption has moved from pilots to production use cases. Every team is deploying LLMs into production, but what does it take to make this work organization-wide, and at scale?

​At LLMs in Prod: SF Chapter, you’ll hear directly from AI leaders at top companies already running mission-critical LLM systems. They’ll share the use cases delivering real value, the lessons learned along the way, and the strategies they use to keep AI reliable and governed.

​We’ll also explore the Model Context Protocol (MCP)—its role as a foundation for AI agents, and what early implementations reveal about interoperability, governance, and scaling AI safely.

​This is a space for AI leaders and teams to learn from peers who are already operating production AI at scale.