Crafting high quality synthetic datasets from scratch

One of the most common mistakes in GenAI application development is the lack of a solid evaluation dataset—without one, you’re left guessing and relying on intuition. Yet in many cases, we have no access to any data, let alone real user feedback. So, how do we move forward? Below, you will learn how to quickly generate high-quality data that facilitates application prototyping.

Bringing clarity to >1M documents with LLM structured output

With powerful LLMs widely available, processing millions of documents is becoming a common scenario, even for smaller projects. Regular API queries simply don’t cut it for this volume—they’re too slow and error-prone—making batch processing the obvious choice. For my recent project, I picked Gemini 2.0 Flash via Vertex AI.

Effortless data insights with semantic search & graph queries

Using natural language to explore databases unlocks new opportunities for non-technical users. This tool, built with Neo4j and LangChain, combines semantic search and graph queries to provide intuitive, code-free access to data insights.

Enhancing legal document copilot accuracy with RAG

I recently explored how to leverage large language models for legal document creation while maintaining their original precision and relevance. A widely-used solution is RAG (Retrieval Augmented Generation) that allows AI to access and use specific document repositories when generating responses.

Exploration vs explanation – engaging citizens through data visualizations

Introductory talk about data visualization and online storytelling – the key concepts, best practices, as well as the most common mistakes (and how to avoid them).

Exploring Bratislava parks through Instagram data

Instagram posts offer a unique window into city life, highlighting urban spaces, revealing resident aspirations, and showcasing public activities. Our research project demonstrates that this social platform can serve as valuable data for urban research and analysis.