WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 North America • Sep 24, 2026 • Session details

Manufacturing trust: speed and safety in the age of agents

Mark Cavage , Michael Irwin , Hervé Bizira

Stop relying on AI to police itself. Discover how Docker's new micro-VM sandboxes help developers embed deterministic boundaries to safely scale multi-agent production and secure autonomous code.

Pause
Mute Enter Fullscreen
#1 about 4 min

Security risks of running autonomous AI agents

Probabilistic models given access to local systems will inevitably probe and dissolve standard container boundaries.

#2 about 4 min

Isolating agents with micro virtual machine sandboxes

Replacing standard containers with shared-nothing micro VMs ensures hard boundaries that autonomous models cannot rewrite.

#3 about 5 min

Enforcing deterministic policies to prevent semantic agent attacks

Grounding probabilistic agent actions in deterministic rules prevents models from abusing legitimate access permissions.

#4 about 2 min

Managing collaborative agent workflows as software production factories

Scaling from individual tools to agent teams requires engineering explicit roles, handoffs, and operational definitions.

#5 about 2 min

Core requirements for scalable agent production architectures

Effective agent factories depend on strict containment, operational control, tooling choice, and reproducible compute capacity.

#6 about 3 min

Standardizing agent environments with Docker Sandbox Kits

Extending Dockerfiles to define agent capabilities, network access, and tools ensures reproducible execution across platforms.

#7 about 5 min

Capturing institutional knowledge using self-learning agent traces

Deploying sovereign AI stacks allows organizations to safely capture problem-solving traces and build collective wisdom.

#8 about 6 min

Injecting credentials and applying network proxies in sandboxes

Executing agents within strict micro VMs allows developers to securely proxy network requests and inject credentials without leaking secrets.

#9 about 4 min

Scaling autonomous workflows with Docker Cloud Sandboxes

Transitioning local agent workloads to cloud infrastructure provides the necessary capacity to run large-scale collaborative models.

Matching moments

5:54 min

Mitigating operational risks through robust agent sandboxing

Isaac Evans Isaac Evans · World Congress 2026 North America

5:22 min

Securing open source agents and orchestrating multiple models

Laura Salinas Laura Salinas · World Congress 2026 North America

2:31 min

Core architectural pillars of an agent sandbox environment

Ivan Burazin Ivan Burazin · World Congress 2026 North America

3:40 min

Scaling and managing multiple AI models in sandboxes

Dan Ndombe Dan Ndombe · World Congress 2026 North America

2:14 min

Setting up local AI sandboxing with Docker SBX

Dan Ndombe Dan Ndombe · World Congress 2026 North America

1:44 min

Generating engineering impact through sandboxed multi-agent experimentation

Julia Kordick Julia Kordick · World Congress 2026 Europe

More from World Congress 2026 North America

2026 in LLMs (so far) thumbnail
31:31
10 days ago

2026 in LLMs (so far)

Simon Willison

Running Operations Without Humans in the Loop thumbnail
32:31
10 days ago

Running Operations Without Humans in the Loop

Edward Aryee, Ryan Ries, Yaron Schneider, Chris Hallenbeck, Floriane Gramlich

Beyond the Code: Human-AI Synergies in Product Development thumbnail
17:43
10 days ago

Beyond the Code: Human-AI Synergies in Product Development

Ajita Kanchivakam Ananth

Honey, look! I vibe-coded an OS! thumbnail
30:40
10 days ago

Honey, look! I vibe-coded an OS!

Ian Smith

The Productivity Illusion: What AI Really Changed for Developers thumbnail
24:28
10 days ago

The Productivity Illusion: What AI Really Changed for Developers

Fatih Kadir Akın

Your Evals Passed. Your Agent Just Emptied a Database. thumbnail
21:37
10 days ago

Your Evals Passed. Your Agent Just Emptied a Database.

Tejas Pravinbhai Patel

Related videos

Making “Works on All Machines” Work for Agent Environments thumbnail
30:54
World Congress 2026 North America • 13 days ago

Making “Works on All Machines” Work for Agent Environments

Michael Irwin

Give the Agent Its Own Machine thumbnail
26:07
World Congress 2026 North America • 13 days ago

Give the Agent Its Own Machine

Dan Ndombe

rm -rf: Horror Stories From Unsandboxed AI Agents (and How Docker Fixes This) thumbnail
25:41
World Congress 2026 North America • 11 days ago

rm -rf: Horror Stories From Unsandboxed AI Agents (and How Docker Fixes This)

Rishab Kumar

One Boundary for the Agentic Era thumbnail
32:01
World Congress 2026 North America • 11 days ago

One Boundary for the Agentic Era

Mark Lechner

Tools, Sandboxes, and the Plumbing of Agentic Development thumbnail
31:21
World Congress 2026 North America • 13 days ago

Tools, Sandboxes, and the Plumbing of Agentic Development

Oleg Šelajev

Supply Chain Security When Agents Write the Code thumbnail
27:08
World Congress 2026 North America • 13 days ago

Supply Chain Security When Agents Write the Code

Ajeet Raina

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.