Revoking Agents and the Rise of the AI Security Engineer
Details
Hey London, we're back for another AI Security Engineers meetup! Brace yourselves for an evening of learning and great conversations.
AI agents no longer just generate text. They call tools, investigate systems and take real actions. So how do you keep them in check? Hammed Ajibade opens with a very practical question: how do you revoke an AI agent? He'll walk through approval boundaries and audit trails for engineering workflows. Then Gerald Crescione, who leads the AI Security Engineers Community at Snyk, makes the case for why we need AI Security Engineers, a role at the crossroads of software, security and AI engineering.
Doors open at 18:00, talks start at 18:30, and as always, food and drinks are on us 🍕🍻! Come hang out with fellow practitioners who are building and securing AI systems.
Agenda
- 18:00 Doors open
- 18:30 Talks start
- 19:30 Social time
- 20:30 End
Venue: Snyk London, Mainframe Building (Euston), Floor 3, 24 Eversholt Street, London NW1 1AD
Speakers
Hammed Ajibade (https://www.linkedin.com/in/hammed-ajibade-010bb2116/) - How Do You Revoke an AI Agent? Approval Boundaries and Audit Trails for Engineering Workflows
This talk examines what changes once an AI agent can do more than generate text: when it can access tools, investigate systems and potentially trigger consequential actions. It addresses how to structure read, recommend and execute permissions, where to place human approval points, and how to apply scoped credentials and revoke them. It also covers how to leave a useful evidence trail across an agent workflow.
Hammed Ajibade is a Lead Software Engineer at Pulse. He builds and leads software across payment systems, platform engineering, mobile products and practical AI tooling. His work sits close to money movement, where systems have to stay reliable under real use.
Gerald Crescione (https://www.linkedin.com/in/geraldcrescione/) - Why We Need AI Security Engineers
Software has changed: AI now writes our code, lives inside our applications and operates our systems, yet security ownership hasn't kept up. Everyone owns a piece of the puzzle, but no one owns the whole system. This talk looks at how AI is reshaping the attack surface and why AI-based security tools are powerful but probabilistic. It argues that deterministic controls, AI systems and human judgment must work together, and it introduces the AI Security Engineer, a role combining software, security and AI engineering. It closes with how to find, train and connect these practitioners.
Gerald Crescione leads the AI Security Engineers Community at Snyk, which runs meetups through 30+ local chapters worldwide. He works at the intersection of building with AI and cybersecurity.
