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
Creators & Guests
You can also support my content by subscribing to my YouTube channel and my weekly newsletter at bret.news!
Grab the best coupons for my 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
