Less Model, More Architecture: Designing AI Systems You Can Actually Trust
Andrei's talk presents a different approach: use AI as an orchestrator of deterministic tools and well-defined workflows, rather than as the final decision-maker. Drawing on practical experience building AI capabilities for a KYC/AML compliance platform, we’ll explore architectural patterns that make AI systems more reliable, traceable, and trustworthy.
Wednesday, September 23rd 2026, 18:00 - 20:00