Infrastructure for Agentic Workloads: From Prototype to Production Without the Pain

​Agentic AI is pushing developer tools into a new era where systems don’t just assist, but reason, adapt, and act within real engineering workflows. Moving from demos to reliable production requires more than clever prompts. It requires the right infrastructure for agentic workloads.

​Join us in San Francisco for a panel with executive leaders building the next generation of AI-native devtools, from autonomous code review to living knowledge systems and local-first IDE agents.

• ​Chang She — Co-Founder & CEO @ LanceDB

• ​Devin Stein — CEO @ Dosu

• ​Ty Dunn — Co-Founder & CPO @ Continue

• ​Harjot Gill — CEO @ CodeRabbit

​We’ll discuss what it takes to run agentic systems in production, including the architectural tradeoffs, infrastructure decisions, and lessons learned scaling from prototype to real-world deployment.

​We’ll focus on building agentic workloads that can reason, take action, and remain robust, observable, and controllable in production.

​By your hosts, LanceDB & Dosu.