Get it on Google Play

Docker and Sandboxing AI Agents

Docker and Sandboxing AI Agents

Author: Software Engineering Daily July 30, 2026 Duration: 50:50
Software Engineering Daily
NewsTechnology

The most useful coding agents can mutate their environments by downloading packages, writing files, and connecting to services across the network. However, that freedom also presents dangers, and promises to usher in a new wave of security threats.

Docker recently announced Docker Sandboxes, which give each agent its own isolated micro VM while preserving the familiar ergonomics of a container. A standard container shares the host’s kernel, but a micro VM emulates hardware and runs its own kernel, giving a stronger security boundary around code that cannot be trusted.

Mark Cavage is the President and COO of Docker, and he previously worked at companies including Stripe, AWS and Oracle. In this episode, Mark joins Gregor Vand for a wide-ranging conversation that includes why agents break the immutability assumptions containers were built on, how micro VMs differ from both containers and traditional VMs, and the still-unsolved challenge of giving agents scoped, trustworthy access to sensitive services and data.

Sponsorship inquiries: sponsor@softwareengineeringdaily.com

The post Docker and Sandboxing AI Agents appeared first on Software Engineering Daily.


Dive deep into the conversations that shape how we build and understand complex systems with Data Archives-Software Engineering Daily. This podcast pulls from a rich library of technical discussions, each one a focused exploration into the specific tools, architectures, and challenges that define modern software engineering. Rather than surface-level news, these episodes offer sustained, thoughtful dialogues with the engineers and thinkers who are working on the front lines of data infrastructure, distributed systems, and emerging technologies. You'll hear detailed breakdowns of real-world problems and the nuanced solutions teams are implementing, providing a practical sense of how theoretical concepts translate into production code and resilient platforms. The archive serves as an enduring resource, whether you're looking to grasp the fundamentals of a new database or understand the intricate trade-offs in a system design. Tune in for a consistently substantive listen that treats software engineering with the depth and seriousness it deserves, all through the unfiltered lens of expert conversation.
Author: Language: en-us Episodes: 50

Official website RSS
youtubelinkedinspotifyapple_music
Software Engineering Daily
Podcast Episodes
A Rust Framework to Simplify Distributed Systems [not-audio_url] [/not-audio_url]

Duration: 50:31
A Rust Framework to Simplify Distributed Systems Building software that runs across many machines is notoriously difficult. Developers have to grapple with problems such as race conditions, partial failures, and message…
Moving Beyond RAG with Precomputed Context [not-audio_url] [/not-audio_url]

Duration: 55:48
Retrieval has become one of the central problems in building useful AI systems. The standard approach to grounding a model in one’s own data has been retrieval augmented generation, or RAG, where an agent searches a vect…
The Death of Online Anonymity [not-audio_url] [/not-audio_url]

Duration: 52:42
Age verification is reshaping how people access the internet. An ever-growing patchwork of laws can now require government IDs, facial age estimation, or behavioral inference before you can enter digital spaces. Discord,…
TypeScript 7 and What Comes Next [not-audio_url] [/not-audio_url]

Duration: 57:15
TypeScript is a programming language that builds on JavaScript by adding a system of types. Those types let developers describe the shape of their data and catch mistakes before code ever runs, while also powering the au…
The Gap Between AI Spending and AI Value [not-audio_url] [/not-audio_url]

Duration: 54:42
It is widely reported that a gap has emerged between enterprise spending on AI and the durable value captured from that spend. Individual employees have enthusiastically adopted coding assistants and chatbots, yet those…
AI and the New Global Security Landscape [not-audio_url] [/not-audio_url]

Duration: 1:12:32
The conversation about AI often focuses on software, automation, and the race between attackers and defenders in code. However, some of the most consequential risks lie further afield, in domains where a mistake is measu…
How LLMs Are Reshaping Recommendation Systems [not-audio_url] [/not-audio_url]

Duration: 47:51
News feeds and recommendation systems have long relied on deep learning architectures that score each candidate item independently. As LLMs have matured, they have opened up a fundamentally different approach, where a sy…
Rebuilding the Cloud for AI Agent Code [not-audio_url] [/not-audio_url]

Duration: 49:57
For two decades, the cloud has been shaped by human developers writing code and managing its deployment. Now a growing share of production code is generated by LLMs with little human review. Because that code is not full…
SED News: The Kimi Moment, Runaway AI, and Tokenmaxxing [not-audio_url] [/not-audio_url]

Duration: 48:28
SED News is a monthly podcast from Software Engineering Daily where hosts Gregor Vand and Sean Falconer break down the biggest stories shaping software engineering, Silicon Valley, and the broader tech industry. In this…

12345»