This talk presents an architectural approach to AI quality assurance in which a second AI system plays the role of a “judge,” replacing traditional testing methods. Using our real-world AI Calories Tracker an application that recognizes 5,000+ food photos every day, we will demonstrate how this unconventional strategy lets us manage risk effectively and boost trust in artificial intelligence.

Imagine one day your team inherits a system that was built over 4 years by six different teams — just to test hypotheses. No documentation. Just a massive monorepo and Jenkins for deployment. That’s exactly what we were handed, and that’s when we decided to take full inventory — starting with Architecture as Code. In this talk, I’ll share how we approached architectural documentation systematically: from building C4 diagrams to creating Service Documentation, ERDs, and Sequence Diagrams. You’ll learn how we practically restored our understanding of the system, brought architectural clarity, and which tools (PlantUML, Mermaid) and methods worked best. This talk isn't just about diagrams — it's about surviving chaos, synchronizing a team, and driving architectural evolution through transparency.

How to properly plan global changes in a company with over 25,000 clients. Why communication between technical teams and the business is the key to success. SRE, R&D, and Architecture as drivers of transformation. The role of FinOps in sustainable development. Real-life cases, mistakes, and lessons learned.