Microsoft Developer: Scale One AI Agent Across Sites (Part 2)

Manufacturers don't have to choose between running AI agents in the cloud or on site. A hybrid model uses one agent framework, built on common data contracts and guardrails, so the same agent runs in the cloud, at the edge, or fully disconnected, with every instance managed through a single interface.

Christoph Berlin, Vice President of Engineering for Cloud and AI at Microsoft, picks up from Part 1's root cause example to tackle scale: how to run an agent across many sites without building it over and over. He closes with two lessons for agentic AI in manufacturing.



Resources

- Microsoft for Manufacturing https://www.microsoft.com/AI/manufacturing

- More Azure resources! https://azure.com/AzureEssentials



Connect

- Christoph Berlin https://www.linkedin.com/in/christophberlin



Chapters

0:00 Why manufacturers can't run every AI agent in the cloud

1:10 Should AI agents run in the cloud or at the edge?

1:49 How a blueprint makes AI agents repeatable

2:25 How one AI agent runs across hundreds of sites

3:04 Two lessons for scaling agentic AI in manufacturing