Sergi López
AI Security Engineer, Almaia
Sergi López is an AI Security Engineer at Almaia, where he works on the security architecture of agentic and memory-persistent AI systems: prompt injection, trust boundaries, and how autonomy changes the threat model.
He also writes on human-AI collaboration — how augmented intelligence compares with full automation, and what changes when a system is designed to work alongside a person rather than replace them.
Why Agentic AI's Vulnerability Is Architectural, Not Just Tactical
Prompt injection surged 340% in 2026 and is now OWASP's #1 AI risk. It is not a filtering problem — it is an architectural one, and stateless agentic systems cannot patch their way out of it.
Human-AI Collaboration: Why Augmented Intelligence Outperforms Full Automation
Discover why the best AI outcomes come from collaboration, not replacement. Learn how enterprises gain 34% more value when AI augments human judgment rather than replacing it.