Running sandboxes at scale can get painful. How do you manage a thousand concurrent sandboxes? We'll cover burst traffic, fast sandbox creation under load, resource exhaustion, shared state with volumes, and per-user data isolation. Then you'll trigger each failure, implement fixes, and see the cost impact in real time. You'll leave with hands-on experience debugging sandbox failures and a set of observability and scaling patterns you can start implementing.
Workshops Day 1 sessions at AI Engineer World's Fair 2026 in San Francisco.
Monday, June 29, 2026
11:05 AM - 12:05 PM·1h
Track 3 · Room 2003
Capacity: 250 attendees
Sign in to add this talk to your schedule.

Matt Brockman
AI Engineer
E2B
@badphilosopher
Matt Brockman is an AI engineer at E2B, the sandbox infrastructure company powering AI agents at companies like Manus, Genspark, and Groq. Before E2B, he was the CTO at Julius AI, where he spent years making AI agents work reliably for data analysis safely in production. He's been building with sandboxes since before most people knew they needed one.