# Guardrails at the Infrastructure Layer: Sandboxing and governing Agentic AI in production

PyTorch Conference North America 2026 · [All sessions](https://sessionize.com/api/v2/s2rq62nk/view/markdown)

- **Session ID:** 1244699
- **When:** Tuesday, October 20, 2026 3:50 pm - 4:20 pm (Pacific Standard Time, UTC-08)
- **Room:** Community Expo (Concourse Level)
- **Speakers:** Sai Charan Teja Gopaluni, Aaresh Sharma

## Description

Agentic AI systems can execute code, call tools, and take multi-step actions autonomously - so where do safety guardrails actually live? Application-level filters aren't enough when an agent has shell access or can orchestrate across services. This BoF explores infrastructure-level approaches to governing agentic AI in production. Let's discuss together:

1/ Container sandboxing for agent tool execution - network policies, seccomp profiles, and runtime isolation on Kubernetes
2/ GPU-level resource boundaries - preventing one agent's runaway inference from starving safety-critical workloads
3/ Observability as governance: audit trails, token-level logging, and kill switches for agentic chains

Located across from the PyTorch gear store.

## Speakers

- [Sai Charan Teja Gopaluni](https://sessionize.com/api/v2/s2rq62nk/view/markdown/speaker/98098927-a120-47ec-b30f-969ce7b14956) — Amazon Web Services, Sr. Specialist SA, GenAI & Agentic Platform
- [Aaresh Sharma](https://sessionize.com/api/v2/s2rq62nk/view/markdown/speaker/004a5326-eb16-403f-98ba-b15cf018b27c) — Sr. Specialist SA - Containers