Skip to content

BRK425 Breakout Wed 18 Nov 13:45 PST

Secure and manage AI workloads at enterprise scale with AI Gateway

Mike Budzynski, Facundo Santiago, Raghu Balam

Summary

From the recording

Microsoft announced Azure AI Gateway as generally available, stating this took effect the day before the session. It is available in 16 Azure regions, with more being added, and supports automated scaling and private connectivity. Auto model selection, which uses the Microsoft Foundry router, is in preview. The gateway mediates agent traffic to models and MCP servers, with Entra authentication, layered policies and OpenTelemetry observability. Demos covered alias-based failover and blocking a leaked secret. Caveat: pricing, exact GA date and whether GA covers every demonstrated feature were not stated; captions are auto-generated.

Session description

Microsoft's catalogue description

As AI adoption grows, IT teams need consistent controls across the models, tools, MCP servers, applications, and agents used throughout the enterprise. Learn how AI Gateway provides a centralized runtime layer to secure, govern, monitor, and manage AI interactions across Microsoft Foundry, Microsoft Agent 365, and applications built anywhere. See how to implement policies, manage cost and traffic, monitor usage, and operationalize AI governance across development and production environments.

← All sessions