WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 9, 2026 • Session details

The day the chatbot asked for sudo

Alex Olivier

When an AI agent asks for system privileges, probabilistic guardrails become useless. Learn how a zero-trust runtime layer stops prompt injections by authorizing the action, not the answer.

Pause
Mute Enter Fullscreen
#1 about 3 min

The risks of deploying untethered AI agents

How running agents under excessive user permissions creates significant security vulnerabilities.

#2 about 2 min

From read-only models to excessive agency

The transition from read-only AI applications to autonomous agents and the resulting security risks.

#3 about 2 min

The missing sandbox in current agent patterns

Why naive tool exposure models and eager autonomous modes lack essential governance and gateways.

#4 about 3 min

Four core challenges for production agents

The critical need for auditability, governance, drift control, and fine-grained kill switches in agentic systems.

#5 about 2 min

Authorizing the action instead of the prompt

Why organizations must switch from prompt engineering safety to deterministic execution constraints.

#6 about 2 min

Applying external policy to agent actions

Using external policy-based access control engines to evaluate and enforce rules on AI tooling requests.

#7 about 5 min

Reference architecture for secure agent deployments

A structured framework leveraging agent sandboxes, egress proxies, and workload identities for governance.

#8 about 5 min

Live demo: Handling support actions deterministically

How a support agent is constrained by policy to respect identity, token exchange, and tool permission scope.

#9 about 3 min

Live demo: Stopping prompt injections dynamically

Utilizing deterministic task binding and policy to prevent unauthorized actions triggered by malicious inputs.

#10 about 2 min

Surgical kill switches and forensic auditing

How externalizing policy checks enables pinpoint revocation of misbehaving agents and complete forensic trails.

#11 about 4 min

Best practices for surviving production AI

Core principles for safer autonomous systems including workload identities, step-down authorization, and task binding.

Matching moments

1:11 min

Shifting security models from passive chatbots to active agents

Péter Farkas Péter Farkas · Europe 2026 Virtual

2:28 min

Mitigating excessive agency through scoped tool access

Deepu Deepu · WWC 2025

1:55 min

Current state of security in AI applications

Deepu Deepu · WWC 2025

3:42 min

Securing AI agents through scoped authorization

Justin Kitagawa · Coffee With Developers

4:15 min

Security integration and AI skepticism in developer tooling

Chris Heilmann +2 · LIVE

3:51 min

Governing and auditing internal AI agents for security

Michele Zuccala Michele Zuccala +4 · WWC Europe 2026

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
about 1 month ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
about 1 month ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
about 1 month ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
about 1 month ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
about 1 month ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
about 1 month ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Upcoming sessions on this topic

Open session

World Congress 2026 North America

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

Abdel Fane

Founder of OpenA2A

Abdel Fane
Open session

World Congress 2026 North America

Responsible AI Architecture with Zero Trust Agents

Ashok Prakash

Staff ML Engineer at Apple

Ashok Prakash
Open session

World Congress 2026 North America

SecurePrompt: Building a Pre-Flight Security Layer for Agentic AI

Ravi Sastry Kadali

AI/ML Engineer at General Motors

Ravi Sastry Kadali
Open session

World Congress 2026 North America

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Yoav Gal, Dor Cohen

Yoav Gal
Dor Cohen
Open session

World Congress 2026 North America

Give the Agent a Budget, Not a Token

Sachin Malhotra

MTS @Anthropic

Sachin Malhotra
Open session

World Congress 2026 North America

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Principal Engineer at Cadence

Vivek Pandit

Related videos

From Shadow AI to Secure Intelligence: Safe AI Usage in the Enterprise thumbnail
34:52
Europe 2026 Virtual • about 1 month ago

From Shadow AI to Secure Intelligence: Safe AI Usage in the Enterprise

Péter Farkas

Building Agents Securely at Scale - Alfonso Graziano thumbnail
31:49
Coffee With Developers • 4 months ago

Building Agents Securely at Scale - Alfonso Graziano

Alfonso Graziano

Headless by Design: Building Enterprise Systems That Agents Can Actually Use thumbnail
23:52
WWC Europe 2026 • about 1 month ago

Headless by Design: Building Enterprise Systems That Agents Can Actually Use

Dirk Gronert

The Private AI Platform: Why Agentic Apps Need a Private Application Platform thumbnail
29:02
WWC Europe 2026 • about 1 month ago

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

Oren Penso

Agentic AI: building autonomous systems for developers thumbnail
28:58
WWC Europe 2026 • about 1 month ago

Agentic AI: building autonomous systems for developers

Anshul Jindal, Sebastian Mahr

The Agent Interface Layer: Protocols, Tools and Trust Boundaries thumbnail
29:34
WWC Europe 2026 • about 1 month ago

The Agent Interface Layer: Protocols, Tools and Trust Boundaries

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

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.