Show Notes
The Daytona founders - Ivan Burazin and Vedran Jukic - discuss their pivot to an AI agent cloud. We dig into the new infrastructure requirements of developing agents that need their own sandboxes to operate in. A year ago, we had them on to talk about Daytona giving us remote development environments for humans, and they have now pivoted the company to focusing on providing cloud hosting environments for AI agents to operate. I suspect this is something we're all gonna eventually need to tackle as we work to automate more of our software engineering. So we spend time breaking down the concepts and the real world needs of humans developing agents, and then the needs of AI that require places to run their own tools in code. Check out the video podcast version here https://youtu.be/l8LBqDUwtV8
😇 My new GitHub Security workshop has launched! A free 2-hour workshop with hands-on labs to harden your repos and your workflows from common supply chain attacks. I'll cover how attackers are getting in, and then we'll lock down a sample repo so you know what needs to be done to protect your code. You'll leave with a deep understanding of risks and mitigations as well as a list of helpful tools to keep your repos safe, including my new "gasa" tool for scanning your repos and orgs. Creators & Guests
Cristi Cotovan - Editor
Bret Fisher - Host
Beth Fisher - Producer
Ivan Burazin - Guest
Vedran Jukic - Guest
You can also support this podcast by subscribing to my YouTube channel and my monthly newsletter at bret.news! Grab the best coupons for my GitHub, Agents, Docker, and Kubernetes courses. Join my cloud native DevOps community on Discord. Grab some merch at Bret's Loot Box Homepage bretfisher.com
(00:00) - Intro
(06:08) - Daytona's Sandbox Technology
(12:57) - Practical Applications and Use Cases
(14:29) - Security and Isolation in AI Agents
(17:59) - Start Up Times for Sandboxing and Kubernetes
(22:51) - Daytona vs Lambda
(31:06) - Rogue Models and Isolation
(34:54) - Humanless Operations and the Future of DevOps
(47:17) - SDK vs MCP
(50:15) - Human in the Loop
(51:13) - Daytona: Open Source vs Product Offering
★ Support this podcast ★
More from DevOps and Docker Talk: Cloud Native Interviews and Tooling
Control Plane CEO Doron Grinstein joins me to discuss how they’ve created an AI-native cloud API that virtualizes multi-cloud and hybrid cloud to simplify management and ship faster. Watch the video of this episode.
What does an AI-native CI look like? The Semaphore team joins me to talk about their focus on making your agent harness the gateway to testing, fixing, and deploying your code. Video podcast version here: https://youtu.be/HzXAdtVrW70
OpenChoreo is a “batteries included”, AI-native Kubernetes platform stack for Platform Engineers that combines GitOps, Observability, AI Agents, and Workflows into a custom K8s distribution “super pack” that is managed via Backstage, CLI, API, or MCP. Check out the video podcast version here: https://youtu.be/AqGWjxEfj2g
Michael Irwin of Docker joins me to run through Gordon AI improvements, Docker Hardened Images and what's now free, Docker Sandboxes for running agents in proper isolation, Model Runner updates including MLX support on Mac, MCP Toolkit dynamic discovery, and the newly renamed Docker Agent with its GitHub Action for automating PR reviews and docs checks. Check out the video podcast version here: https://youtu.be/dTF3b36Bq6w
Bret is joined by the founders of Plakar - Julien Mangeard and Gilles Chehade - to nerd out over backup engineering. The kind where you're building your own file formats and cryptographic layers, not just wiring up cron jobs. We get into how Plakar deduplicates and encrypts at the source so your cloud provider never sees your keys. Also, their snapshot model has no chain dependencies, which means you can delete any backup without breaking the others. We had a fun hour of backup horror stories, ransomware pragmatism, where I'm lobbying hard for a Docker volume integration. Check out the video podcast version here: https://youtu.be/OPRK5osKQHI