WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 North America β€’ Sep 26, 2026 β€’ Session details

One Boundary for the Agentic Era

Mark Lechner

Are autonomous AI agents exposing your infrastructure to unseen supply chain risks? Discover how Docker sandboxes and the new Kit specification enforce secure, observable boundaries as code.

Pause
Mute Enter Fullscreen
#1 about 3 min

Security risks of delegating agency to autonomous systems

Delegating open-ended tasks to autonomous agents amplifies existing access vulnerabilities and persistence risks.

#2 about 3 min

Establishing an isolated execution boundary for agents

Isolating agent workloads within a dedicated environment limits the impact of unexpected or malicious actions.

#3 about 3 min

Enforcing network access and securing credential injection

Enforcing network policies outside the workload ensures malicious tools cannot compromise host credentials or services.

#4 about 3 min

Observing agent behavior and investigating unexpected access

Correlating workload identity and purpose with access logs enables accurate attribution of autonomous actions.

#5 about 2 min

Evaluating agent artifacts with verified building blocks

Reusing evidence from verified base components focuses security reviews entirely on newly generated outputs.

#6 about 5 min

Simulating agent interactions within an isolated runtime

Setting up a secure sandbox environment demonstrates how bounded agents interact with local registries and APIs.

#7 about 6 min

Defining agent capabilities using configuration as code

Managing agent manifests as code provides implicit observability and dynamically generates security monitoring rules.

#8 about 6 min

Troubleshooting sandbox deployments and credential configuration failures

Unexpected expired credentials and configuration challenges illustrate the complexities of debugging autonomous agent deployments.

#9 about 5 min

Monitoring application layer policies and dynamic alerting

Collecting network logs from the sandbox daemon enables dynamic alerting and precise attribution for agentic events.

Matching moments

5:54 min

Mitigating operational risks through robust agent sandboxing

Isaac Evans Isaac Evans Β· World Congress 2026 North America

3:12 min

Securing agent interactions using persistent identity and sandboxed environments

Vlad Luzin Vlad Luzin Β· World Congress 2026 North America

3:22 min

Evaluating security risks and capabilities of the agentic web

Meta Atamel +1 Β· Coffee With Developers

4:47 min

Reference architecture for secure agent deployments

Alex Olivier Alex Olivier Β· World Congress 2026 Europe

3:04 min

Demystifying the core technical layers of agent architectures

Taylor Jordan Smith Taylor Jordan Smith Β· World Congress 2026 Europe

4:10 min

Implementing security through core software engineering principles

Mitesh Patel Mitesh Patel +3 Β· World Congress 2026 North America

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 AkΔ±n

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

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

Supply Chain Security When Agents Write the Code

Ajeet Raina

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

Give the Agent Its Own Machine

Dan Ndombe

Manufacturing trust: speed and safety in the age of agents thumbnail
31:59
World Congress 2026 North America β€’ 12 days ago

Manufacturing trust: speed and safety in the age of agents

Mark Cavage, Michael Irwin, HervΓ© Bizira

Making β€œWorks on All Machines” Work for Agent Environments thumbnail
30:54
World Congress 2026 North America β€’ 13 days ago

Making β€œWorks on All Machines” Work for Agent Environments

Michael Irwin

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

Tools, Sandboxes, and the Plumbing of Agentic Development

Oleg Ε elajev

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

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

Rishab Kumar

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.