WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
Aug 21, 2026

How to Stop Your Agents From Going Rogue - Arnav Gupta

Arnav Gupta warns that deploying autonomous AI agents without guardrails is a disaster waiting to happen. Learn how open-source runtime security stops rogue systems from deleting your production data.

Starting at 21:29 · Watch from the beginning

How to Stop Your Agents From Going Rogue - Arnav Gupta thumbnail

Checking access…

Playback and chapters load privately for Free videos.

Matching moments

1:53 min

Introduction to securing open source AI agent infrastructure

Abdel Fane Abdel Fane · World Congress 2026 North America

1:03 min

From read-only models to excessive agency

Alex Olivier Alex Olivier · World Congress 2026 Europe

2:09 min

Balancing AI adoption with emerging security realities

Desmond Lamptey Desmond Lamptey · World Congress 2026 North America

4:15 min

Security integration and AI skepticism in developer tooling

Chris Heilmann Chris Heilmann +2 · LIVE

6:19 min

Preventing automated disasters with practical agent guardrails

Sachin Malhotra Sachin Malhotra · World Congress 2026 North America

3:24 min

The evolution of autonomous AI agents and workflows

Dan Ndombe Dan Ndombe · 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

Your AI Agents Are Bleeding Tokens: Building a Runtime Cost Control Plane for LLMs

  • Aakriti Aggarwal

    IBM Research

    Research Engineer

  • Bhavishya Pandit

    66degrees

    Leading AI Innovation

Open session

Your AI Wrote the Code. Who Vouches for It?

  • Siddharth Joshi

    GitHub

    Senior Customer Success Architect

Open session

Speed or Security? Why Not Both for Your Coding Agents

  • Ajeet Raina

    Docker

    Developer Advocate

Open session

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

  • Navin Pai

    StackGen

    Director of Engineering

Open session

Ship Happens: Guardrails for AI-Written Code

  • Anthony Nguyen

    LaunchDarkly

    Senior Solutions Engineer

Related videos

The day the chatbot asked for sudo thumbnail
27:48

The day the chatbot asked for sudo

Alex Olivier · Cerbos

World Congress Europe · 2026

Codifying Trade-offs: Security, Cost, and Compliance as Agent Guardrails thumbnail
30:54

Codifying Trade-offs: Security, Cost, and Compliance as Agent Guardrails

Suzanne Daniels · Microsoft

World Congress North America · 2026

Responsible AI Architecture with Zero Trust Agents thumbnail
25:33

Responsible AI Architecture with Zero Trust Agents

Ashok Prakash · Apple

World Congress North America · 2026

The Private AI Platform: Why Agentic Apps Need a Private Application Platform thumbnail
30:35

The Private AI Platform: Why Agentic Apps Need a Private Application Platform

Oren Penso · Tanzu division Broadcom

World Congress North America · 2026

AI Governance & Compliance: Who Is Responsible When the Bots Start Acting? thumbnail
29:29

AI Governance & Compliance: Who Is Responsible When the Bots Start Acting?

Kumesh Aroomoogan +2

World Congress North America · 2026

Securing AI Agent Infrastructure: Identity, Attestation, and Trust at Scale thumbnail
25:54

Securing AI Agent Infrastructure: Identity, Attestation, and Trust at Scale

Abdel Fane · OpenA2A

World Congress North America · 2026

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.