A selection of my work, from commercial platforms to open-source research. Each project is presented as a brief case study, exploring the problem that motivated the work and the principles behind its solution. You'll find interactive visualizations, AI studies, and full-stack web platforms, with links to live demos and source code.
An agentic system addressing the trade-off between speed and reliability in data analysis. By combining AI for creative tasks with deterministic modules for visualization, it generates both explorable reports for readers and verifiable notebooks for analysts. This hybrid approach explores a more transparent and adaptable model for human-AI partnership in generating insights.
A platform for a digital consultancy that required a professional, bilingual online presence with complete editorial control. The system empowers non-technical teams to manage complex multilingual content effortlessly, balancing user autonomy with the performance and reliability needed to serve both local and international markets, without technical dependencies.
An investigation into whether Vision-Language Models perceive scientific visualizations with the same nuance as human experts. The research evaluates 13 state-of-the-art models on a curated set of images, measuring their alignment with expert judgments on visual purpose and encoding patterns, providing a quantitative view of the gap between machine and human perception.
A Python widget that eliminates the friction of creating diagrams in notebooks by integrating the D2 declarative language directly into Jupyter and Marimo. It restores the interactive workflow by providing live, text-based diagramming with inline previews, removing the need for external tools and context switching.
An extension that bridges the gap between static documentation and interactive learning. By embedding runnable UIs directly into Quarto pages, it transforms passive reading into an active, explorable experience, allowing users to experiment with code and observe results instantly, without any backend or local setup.
A platform for a men's health publication that addresses the challenge of aligning editorial strategy with audience needs. It combines a high-performance public site with a lightweight analytics system, providing editors with actionable insights on content gaps and topical balance, moving beyond simple traffic metrics to guide strategic planning.
An exploration into humanizing vehicle telemetry. The project addresses the challenge of translating vast streams of raw automotive data into meaningful, intuitive experiences for drivers, moving beyond mere numbers to provide actionable insights for safer and more efficient mobility.
A tool designed to make the complex ethics of data use tangible. Through a structured questionnaire, it helps organizations and individuals assess the public value of data practices, providing a clear risk-benefit analysis and actionable recommendations to foster trust and accountability in a data-driven world.
A flexible constraint-based system that addresses the rigidity of automated visualization tools. By modeling design expertise as a set of logical rules, it helps researchers and practitioners create effective charts without deep design knowledge. Its core innovation is a renderer-agnostic format, democratizing visualization by making expert knowledge computational and extensible.