WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 North America • Sep 25, 2026 • Session details

Govern the Runtime, Not the Agent: One Control Plane for Every Model, Every Harness

Tushar Jain

Docker CTO Tushar Jain warns that trusting AI agents to self-police is fundamentally flawed. Discover how governing the runtime creates a secure isolation boundary for any AI model.

Pause
Mute Enter Fullscreen
#1 about 4 min

The safety risks of adopting multiple models and harnesses

Embracing different agents and frameworks introduces significant security challenges and breaks implicit trust assumptions.

#2 about 5 min

Establishing a centralized runtime for consistent agent governance

A universal runtime layer provides a critical isolation boundary to enforce deterministic safety constraints across any framework.

#3 about 6 min

Demonstrating deterministic policy enforcement in agent sandboxes

Restricting repository access validates how execution boundaries prevent destructive actions like unauthorized workspace deletions.

#4 about 6 min

Mapping fine-grained policies to semantic organizational context

Moving beyond basic network blocking requires extensible runtime rules that understand specific API methods and internal resource intent.

#5 about 5 min

Leveraging centralized runtimes to optimize and own intelligence

A standardized governance layer provides the observability needed to optimize model routing and train fine-tuned agents.

#6 about 7 min

Managing agent identity and multiplayer enterprise governance

Advancing agent usage requires defining independent credentials and managing shared memory contexts across complex organizational hierarchies.

Matching moments

1:03 min

Establishing runtime governance for scalable enterprise AI systems

Péter Farkas Péter Farkas · Europe 2026 Virtual

5:22 min

Securing open source agents and orchestrating multiple models

Laura Salinas Laura Salinas · World Congress 2026 North America

5:54 min

Mitigating operational risks through robust agent sandboxing

Isaac Evans Isaac Evans · World Congress 2026 North America

2:08 min

Enforcing runtime boundaries during agent execution workflows

Péter Farkas Péter Farkas · Europe 2026 Virtual

3:40 min

Scaling and managing multiple AI models in sandboxes

Dan Ndombe Dan Ndombe · World Congress 2026 North America

1:03 min

From read-only models to excessive agency

Alex Olivier Alex Olivier · World Congress 2026 Europe

More from World Congress 2026 North America

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

2026 in LLMs (so far)

Simon Willison

Running Operations Without Humans in the Loop thumbnail
32:31
21 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
21 days ago

Beyond the Code: Human-AI Synergies in Product Development

Ajita Kanchivakam Ananth

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

Honey, look! I vibe-coded an OS!

Ian Smith

The Productivity Illusion: What AI Really Changed for Developers thumbnail
24:28
21 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
21 days ago

Your Evals Passed. Your Agent Just Emptied a Database.

Tejas Pravinbhai Patel

Upcoming sessions on this topic

Open session

Speed or Security? Why Not Both for Your Coding Agents

  • Ajeet Raina

    Docker

    Developer Advocate

Open session

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

  • Vikram Vaswani

    Consultant

Open session

Architecting Trusted AI: Coupling Multi-Agent Systems with dbt Semantic Store for Zero-Hallucination

  • Pushkar Mishra

    J.P. Morgan

    Senior Vice President

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

Open session

From Prompt Engineering to Harness Engineering: Building Observable and Governed GenAI Systems

  • Lakshmi Devi Prakash

    JPMorgan Chase

    VP, Applied AI/ML Lead

Related videos

Manufacturing trust: speed and safety in the age of agents thumbnail
31:59
World Congress 2026 North America • 22 days ago

Manufacturing trust: speed and safety in the age of agents

Mark Cavage, Michael Irwin, Hervé Bizira

The day the chatbot asked for sudo thumbnail
27:48
World Congress 2026 Europe • 3 months ago

The day the chatbot asked for sudo

Alex Olivier

One Boundary for the Agentic Era thumbnail
32:01
World Congress 2026 North America • 21 days ago

One Boundary for the Agentic Era

Mark Lechner

Give the Agent a Budget, Not a Token thumbnail
26:00
World Congress 2026 North America • 21 days ago

Give the Agent a Budget, Not a Token

Sachin Malhotra

The Agent Interface Layer: Protocols, Tools and Trust Boundaries thumbnail
29:34
World Congress 2026 Europe • 3 months ago

The Agent Interface Layer: Protocols, Tools and Trust Boundaries

David Soria Parra, Duan Lightfoot, Malte Ubl, Taroon Mandhana

Your Agents Need Observability Before They Need Better Models thumbnail
25:30
World Congress 2026 North America • 22 days ago

Your Agents Need Observability Before They Need Better Models

Julia Furst Morgado

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.