Skip to main content
DevSecCon_2025_Logo_-_light_hor_year_1_if0eww

DevSecCon - AI Demos

Watch the best of DevSecCon ‘25

DevSecCon 2025 virtual summit was a global celebration of innovation in AI Security with inspiring keynotes, hands-on demos, and groundbreaking community-led research. Dive into the sessions from the main stage below and join the global DevSecCon community to help shape the future of secure development.

AI demos track spotlight

Watch this track for interactive, hands-on demos on “Build and Secure with AI.” You'll leave with skills you can immediately apply. Watch the recordings now.

Containerized AI Security: How We Automated Safety at Scale

What happens when you ask your community for submissions, and you want to make sure nothing malicious gets into your codebase? Watch this talk to see how Blocked solved this by having their AI system build its own security scanner for a community-driven project of "automation recipe" submissions.

MCP Threat Trap: Deception Engineering for Zero Trust AI Access

This session is for defenders, detection engineers, and curious red teamers exploring how Zero Trust meets deception engineering in the age of AI orchestration.

Common Pitfalls and How to Avoid Them When Building Production-Ready Multi-Tenant MCP Servers

The Model Context Protocol (MCP) is quickly emerging as the open standard for connecting AI systems to external tools and data sources. Yet for most developers, getting an MCP server from prototype to production still feels like navigating uncharted territory. In this talk, we’ll walk through the real-world pitfalls of building and deploying multi-tenant MCP servers in production.

Build Multi-User MCP Servers (No Headaches Edition)

Building Model Context Protocol servers is a powerful way to extend the capabilities of LLMs, but what happens when you go beyond "works on my machine"? Lurking behind every MCP demo is a complex set of security and authorization questions. In this engaging talk, we’ll walk through how the latest evolution of the MCP spec makes fine-grained, multi-user auth possible and explain the best practices for securing MCP servers in production.

AI Agents Are Here - Are You Ready?

In 2025, the fastest growing user base are AI Agents. They autonomously interact with your system to extract data and perform operations. For some companies - this is a threat that needs to be controlled. For others, it’s an opportunity to allow customers to interact with your systems in a novel way.

Check out all the session tracks from DevSecCon 2025

On-Demand

AI security Research track

View Now

Join our community

DevSecCon is where security enthusiasts learn, share, and shape the future of DevSecOps together.

Ressources supplémentaires

Blog

Foundations of trust: Securing the future of AI-generated code

Learn about Snyk's incoming GenAI Partner Program and how it secures the code produced by AI coding assistants, ensuring developers can code faster and more securely.

Blog

SnykLaunch Oct 2024: Enhanced PR experience, extended visibility, AI-powered security, holistic risk management

Read a recap of our SnykLaunch event for October 2024, covering our new features that power a developer-first, risk-centric security experience.

Blog

Going beyond reachability to prioritize what matters most

While static reachability can help teams better understand their app vulnerabilities, they must be paired with other types of context and risk insights.