Founder & Independent Researcher

I came to this work from a slightly unusual direction.

I spent years investigating fraud, cyber incidents and complex patterns of human behaviour, followed by almost a decade working across data, risk, security and AI governance.

When I started looking closely at AI agents, some of the patterns felt surprisingly familiar: individually legitimate actions combining into outcomes nobody intended, evidence scattered across systems, and accountability becoming difficult precisely when it matters most.

That investigative lens now shapes how I approach AI resilience — looking beyond what a system is supposed or authorised to do to understand what it actually does once deployed.

I founded AI Resilience Lab to investigate that gap and develop practical ways to keep increasingly autonomous AI systems observable, governable and accountable.

LinkedIn ↗