AI as a Product: From Support Automation to the Agentic State in the Diia Ecosystem [ukr]
Implementing AI into a government service with 23+ million users is a journey of continuous product discoveries and challenges. In this talk, I will share the real-world experience of how the "Diia" ecosystem is transitioning from a classic Digital State (where users search for the required services themselves) to an Agentic State (where AI proactively fulfills the user's intent).
-
What we will cover:
- Product Discovery and Paradigm Shift: The transition from Digital State to Agentic State. Why traditional interfaces have reached their limits and how we validated the need for proactive AI solutions
- AI in Support as the First Big Step: How we automated 90% of requests without a drop in quality (CSAT). Soft AI UX: why people struggle with prompting and how we guide them using hybrid interfaces
- The Upskill Case and Team Transformation: We didn't fire a single operator. How we built internal AI tools for the team, turning yesterday's support agents into AI trainers
- Deep Dive into Diia.AI on the Portal: The launch of the world's first agentic service at the government level. How our RAG architecture works, how we architecturally protect personal data (PII) from entering the LLM, and how we repel jailbreak attempts
Denys Korovin
AI Product Manager at WINWIN AI Center of Excellence (Ministry of Digital Transformation of Ukraine)
- Over 7 years of experience building digital products, evolving from a Business Analyst to an AI Product Manager, with a track record of launching solutions from scratch in govtech and fintech
- Responsible for the development and implementation of intelligent AI solutions in public services, specifically within the "Diia" ecosystem (23+ million users)
- Focuses on R&D and customer experience transformation: drives the ecosystem's transition to the Agentic State and directly participated in the release of the world's first agentic AI service at the government level
- Believes that a successful AI product is born only through the synergy of classical Software Engineering and ML, thus acting in practice as a product "bridge" between these teams
- Pursuing a PhD in Computer Science, focusing on turning innovations into working products even when there are no ready-made references or playbooks