About this episode

Scott talks with Mark Cavage about the resurgence of sandboxes as critical infrastructure for AI-assisted development.

Sandboxing is having a moment. As agents move from chat windows into terminals, repos, and production-adjacent workflows, the question is no longer “What can AI generate?” but “Where can it safely run?” In this episode, Scott talks with Mark Cavage, President of Docker, about the resurgence of sandboxes as critical infrastructure for the agent era and the thinking behind Docker’s newly released sandbox feature. They explore why isolation, reproducibility, and least-privilege execution are becoming table stakes for AI-assisted development. From protecting local machines to enabling trustworthy automation loops, Scott and Mark dig into how modern sandboxes differ from traditional containers, what developers should expect from secure agent runtimes, and why the future of “AI that does things” will depend as much on boundaries as it does on model capability.

People in this episode

Host: Scott Hanselman

Guest: Mark Cavage

Topics covered

• AI
• sandboxing
• Docker
• development
• automation
• security

Keywords

• AI agents
• sandbox feature
• isolation
• reproducibility
• least-privilege execution
• secure agent runtimes

Mentioned in this episode

Organizations: Docker

More episodes of Hanselminutes with Scott Hanselman

• Building the Internet with sendmail's Eric Allman · March 19, 2026 · 33 min
• A cognition engine for science with Allen Stewart · March 12, 2026 · 31 min
• Agentic Workflows with Don Syme · March 5, 2026 · 33 min
• Inference Engineering with Baseten's Philip Kiely · February 26, 2026 · 33 min
• That's good Mojo - Creating a Programming Language for an AI world with Chris Lattner · February 19, 2026 · 41 min
• The Rise of The Claw with OpenClaw's Peter Steinberger · February 12, 2026 · 44 min

Explore listener stats, chart rankings, contacts and more on the Hanselminutes with Scott Hanselman podcast page.