Part 2 – Running Your LLM Agent Safely: Hands-on with Docker Sandboxes

​Your LLM agent can now write files, call APIs, and make its own decisions. Do you know where it's allowed to do that?

​That question is exactly what Docker Sandboxes were built to answer. In Part 2 of this Docker-sponsored webinar series, Dan Ndombe — Staff Developer Success Advocate at Docker — leads a 2-hour, hands-on workshop on running LLM agents safely using Docker Sandboxes (SBX).

​This isn't a slide deck. It's a live, code-along session where you'll spin up a sandboxed runtime, give an agent a small task, and watch how containment actually works in practice — then take that pattern straight back to your own projects.

​What You'll Learn
→ How to spin up a sandboxed agent runtime with Docker Sandboxes
→ How to give an agent a real task and watch it execute safely
→ How to tighten policies and permissions around agent behavior
→ Why containing an agent by design beats trusting it by default
→ A repeatable pattern for your own LLM and agent prototypes

​No prior Docker experience required. Seats are limited to keep things interactive.