About
Tom Mooney.
Author of Agentic AI Security — working at the intersection of security leadership and hands-on engineering, on the new attack surface that opens when AI stops talking and starts acting.
Tom leads cloud, data and AI security for a global financial services group, with 15+ years securing complex systems at global scale — from national-security architecture for the UK government to global cloud transformation at a leading technology firm. His focus now is the execution layer of AI security: the permissions, controls and governance that decide what autonomous systems are allowed to do.
The thesis
Autonomy is blast radius.
For a decade, AI security meant worrying about what a model would say. Agentic AI changes the model: these systems now hold credentials, call tools, move data and take actions. The risk is no longer the output. It’s the action.
The more autonomy you grant, the larger the blast radius when an agent is talked into a mistake. Securing that means securing the execution layer — and testing what agents actually do under adversarial pressure, not what their model cards promise.
Background
15+ years securing complex systems at global scale
Financial services, cloud platforms and government
National-security architecture for the UK government
Board-level security leadership in financial services
Executive MBA, University of Cambridge
Author of Agentic AI Security
Per the firm’s policy, current and former employers are abstracted by sector rather than named.
The newsletter
One brief.
Every week.
News, new attacks, and practical guidance for defending AI agents — written for security leaders and the engineers shipping them. Free, and the first three chapters of Agentic AI Security (draft) land in your inbox when you confirm your email.
- First 3 chapters of the book, free
- New threats & incidents
- Defensive patterns & checklists
- Tooling and research worth your time