Run secure agent loops in production with isolated sandboxes at scale | BRK448
Christian Flasshoff, Jeffrey Quesnelle, Devanshi Joshi and Jan Kalis examine the infrastructure needed to move agent workloads into production, with Azure Container Apps sandbox demonstrations and enterprise deployment examples.
Production agents need a platform, not just a model
The session frames production AI agents as a platform problem. Before organizations can trust agents to run workloads, they need secure isolation, identity, governance, observability and cost control.
Azure Container Apps provides the foundation discussed in the session, combining production-ready defaults with microVM isolation and governance. The presenters also explain how Copilot Studio and Foundry Agent Service leverage this architecture and how enterprises can implement it.
Isolation and enterprise controls
The session examines why sandboxed microVMs are becoming a foundation for agent workloads, then connects that infrastructure to practical deployment concerns:
- Isolation and governance: Addressing the risks of running agents in production.
- Scalable infrastructure: Using Azure Container App Sandboxes to support secure agent workloads.
- Network controls: Exploring ingress and egress policies.
- Sandbox capabilities: Demonstrating snapshots and secretless access.
- Operational requirements: Accounting for identity, observability and cost control.
Sandbox demonstrations use the Azure portal, CLI and Visual Studio Code.
Deployment examples: Hermes Agent and Cognite
The Hermes Agent segment covers its development as a production AI agent platform, self-improvement loops, and the governance and security challenges those loops introduce. It also examines how Hermes Agent uses Azure Container App Sandboxes, including its architecture, enterprise controls and lessons from large-scale deployments.
The Cognite segment focuses on industrial AI use cases powered by secure sandboxed agents, alongside insights from production deployments.
Session chapters
- 00:00: Introduction to secure agent loops and sandbox infrastructure
- 01:14: Risks of agents in production and the need for isolation and governance
- 02:34: Why sandboxed microVMs are becoming the foundation for agent workloads
- 04:17: Hermes Agent overview and its rise as a production AI agent platform
- 06:10: Hermes Agent self-improvement loops, enterprise governance and security challenges
- 08:01: How Hermes Agent uses Azure Container App Sandboxes for scalable, secure infrastructure
- 10:07: Hermes Agent architecture, enterprise controls and large-scale deployment lessons
- 16:07: Azure Container App Sandboxes deep dive with portal, CLI and Visual Studio Code demonstrations
- 22:17: Advanced sandbox capabilities: ingress, egress policies, snapshots and secretless access
- 35:02: Cognite industrial AI use cases and production deployment insights
Resource
This intermediate-level Cloud & AI breakout session, BRK448, is part of Microsoft Ignite 2026 and is presented in English (US).