Lean scientific inference
Isolating the signal within the noise. I provide a transparent record of the decisions that transform complex research into disciplined AI applications.
About me
I'm Jason Lo, a builder and repairer of systems, driven by the belief that real efficiency comes from rapid iteration and adaptation. My work is an ongoing experiment in applying cutting-edge AI, spanning neuroimaging, literacy, agriculture, and geoscience, to find the simplest and most robust path to discovery.
Work philosophy
Discovery depends on finding the right scale. I favor minimalism, matching methodology to the problem without unnecessary bloat. Efficiency matters to me, not only in code but in how we learn and adapt at the edge of research.
I build by pruning the nonessential, ensuring each decision is as lean as the science requires. Every significant decision is documented, because effective engineers clarify their thinking, not just their output.
Featured projects
- 2026Skill Sommelier: Claude Code PluginA curated plugin that discovers, manages, and distributes Claude Code skills from GitHub.
- 2025LLM-Assisted Farm Management InsightsBuilt a human-in-the-loop LLM pipeline that converts agricultural research into actionable farm management recommendations, published in Scientific Reports.
- 2024Expert Discovery Platform: RABBITLed the development of an AI-powered semantic search platform that helps UW–Madison researchers, industry partners, and campus collaborators discover faculty expertise.