Evgeniya Ovchinnikova
About
I build solutions that make technology work for people. With experience in AI, data, and automation, I turn real needs into tools that make work faster and smarter.
Trained as a physicist, I moved into data science and innovation to make a more direct impact on real-world problems. Since then, I’ve worked across telecommunications, energy, e-commerce, and insurance—helping teams create technology that delivers real value.
One highlight was helping build a GenAI platform used by more than 48,000 people, saving over 2 million working hours every year. I also contributed to an intelligent system that helps over 20,000 employees share knowledge more easily and work together more effectively.
I enjoy learning, improving, and working with others who want to make a difference. Let’s connect and explore new ideas together.
Session
Keywords: Explainable AI, enhanced RAG, GraphRAG, LLMOps, dialog system evaluation.
Designing reliable dialog flows for LLM-based systems remains challenging once conversations require branching, correction, or multi-step reasoning. Dialog graphs often evolve organically and accumulate structural issues: endless correction loops, dead subpaths, redundant validation steps, overly generic catch-all branches, or linear sequences that should be collapsed. Such phenomena raise operational costs, significantly increase TTFT and make the system answer less predictable and explainable.
Many solutions try to introduce an all-fit generalized RAG retrieval solution. Contrary to this, we present our empirical learnings on how to enhance system speed, lower overall costs and offer a better dialog graph explainability through enhanced LLM call tracing and iterative enhancements for common dialog paths.
We also show that more elaborated knowledge retrieval strategies like GraphRAG may drastically enhance overall response quality and shorten the dialog graph. We evaluate several approaches and give recommendations on how to leverage more complex document indexing phases for inference time benefits.
Overall, the session argues that scalable conversational systems require not only better prompts, but explicit graph structures paired with rigorous tracing and data-driven optimization.