World Congress 2026 Europe • Jul 10, 2026 • Session details

YOLO Developer Workflows with a Coding Agent in a Box

Manuel de la Peña

Stop letting AI agents blindly mutate your host machine. Docker Sandboxes isolate them in secure microVMs to deliver fast, fearless developer workflows without the security risks.

Pause
Mute Enter Fullscreen
#1 about 2 min

The rise of coding agents and YOLO workflows

Developers are giving coding agents full access to their local environments, creating significant security vulnerabilities.

#2 about 4 min

The risks of unconstrained AI agent permissions

Autonomous agents with unfettered access can inadvertently destroy databases, leak credentials, or communicate with unauthorized endpoints.

#3 about 2 min

The Skinner box effect of continuous prompt approval

Automatically accepting agent prompts trains developers to ignore mistakes that only need to happen once to cause catastrophic data loss.

#4 about 1 min

Designing physical infrastructure isolation for AI agents

Moving security boundaries outside the language model into the infrastructure inherently prevents agents from overriding safeguards.

#5 about 2 min

Why standard containers are insufficient for agent workflows

Standard containers struggle with agent-driven state mutations and local permission escalations that allow agents to escape.

#6 about 3 min

Docker sandbox architecture and microVM environment integration

Sandboxing agents inside a microVM equipped with a network proxy and secrets manager delivers secure, isolated workspaces.

#7 about 5 min

Initializing a sandbox environment and managing component secrets

Setting up placeholder secrets prevents agents from directly accessing or exfiltrating actual programmatic credentials.

#8 about 2 min

Managing agent permissions with proxies and declarative kits

A man-in-the-middle proxy dynamically injects real credentials while declarative kits bootstrap sandbox tools and allowed domains.

#9 about 5 min

Exposing ports and monitoring agent network traffic

Safely exposing sandbox ports to the local host ensures developers can interact with agent-built applications without risking host security.

#10 about 2 min

Defining agent boundaries using infrastructure as code configuration

YAML files declare specific allowed domains, environment variables, and install commands to tightly govern agent environments.

#11 about 2 min

Scaling organizational security with Docker AI governance layer

Applying node-level organizational policies ensures developers cannot bypass overarching security principles when running agents.

#12 about 5 min

Installation guidelines and enforcing secure agent practices

Adopting isolated sandboxes rather than dangerous alias commands fosters speed and productivity without exposing systems to costly risks.

Matching moments

5:54 min

Mitigating operational risks through robust agent sandboxing

Isaac Evans Isaac Evans · World Congress 2026 North America

8:48 min

Live demonstration of an application-defined compute coding agent

Anurag Goel Anurag Goel · World Congress 2026 North America

2:22 min

Orchestrating local developer environments with AI tools

Angie Jones Angie Jones · World Congress 2025

7:17 min

Isolating local AI coding agents via Docker Sandbox

Ajeet Raina Ajeet Raina +1 · World Congress 2026 North America

2:34 min

Balancing developer autonomy with the adoption of coding agents

Clemens Wasner Clemens Wasner +4 · World Congress 2026 Europe

4:21 min

Evolving Docker from containerization to an AI ecosystem

Ajeet Raina Ajeet Raina +1 · World Congress 2026 North America

Upcoming sessions on this topic

Open session

Beware of Strangers Bearing Code: Open Source Trust in the Agent Era

  • Vikram Vaswani

    Consultant

Open session

Teaching AI Coding Agents to Build It Right the First Time

  • Sajeetharan Sinnathurai

    Microsoft

    Principal Product Manager

Open session

Beyond File Dumps: Context Engineering for Coding Agents

  • Animesh Dutta

    Arm

    Senior Software Engineer

Open session

Build a Zero-Cost AI Agent in Your Browser

  • Aishwarya Mathuria

    Adobe

    Computer Scientist

  • Nishant Thakur

    Adobe

    Senior Computer Scientist

Open session

Autopsy of an Autonomous Incident: When the Agent Made It Worse

  • Navin Pai

    StackGen

    Director of Engineering

Open session

Java is Coming for Python’s Lunch: The Rise of JVM AI Agents

  • Frederik Pietzko

    Jetbrains

    Developer Advocate