Latent Space: The AI Engineer Podcast Why Every Agent needs Open Source Cloud Sandboxes
1271 snips
Apr 24, 2025 
Vasek Mlejnsky, a visionary from E2B, joins to share insights on building secure cloud sandboxes for AI agents. He discusses the rapid growth of E2B and its adoption by major companies. The conversation dives into the unique challenges posed by early LLMs and the advantages of cloud environments for AI. Vasek highlights practical use cases like code execution and data analysis, while also addressing the shifting landscape of AI frameworks and billing models. His thoughts on future advancements and multi-modality in AI are particularly intriguing.
AI Snips
Chapters
Transcript
Episode notes
Origins of E2B Sandboxes
- Vasek and Tomas started with DevBook, an interactive developer playground for tools like Prisma.
- They pivoted to E2B using sandbox tech to let AI agents run and test code automatically.
AI Model Growth Spurs Sandbox Use
- End of 2024/start of 2025 is when AI shifted from simple code interpreting to computer use and RL use cases.
- Model capabilities drove E2B's growth and expanded sandbox usage for diverse AI workloads.
Educate Developers on Sandboxes
- Market education is key; show developers concrete sandbox use cases like code interpreting first.
- Build trust by guiding users on practical ways to use sandboxes for AI workflows.