Viewing profile — y14

Built an MCP server for data work with memory and rules. Use cases: - Engineers: query your data from Claude/Cursor, debug issues, build with analytics in dev flow (like [1] but wi…

Thanks for the question. Avoiding context bloat and overall engineering the context is (still) most of work. What’s been working: - Role scoped calls: data modeling, code gen, are …

The hardest problems building this weren’t in the LLM logic, but in everything around it —-observability, access control, and managing context across dbt, Tableau, and code. Findin…

Excited to share a project I’ve been building for months! Would love to receive honest feedback :) My motivation: AI is clearly going to be the interface for data. But earlier atte…

Hi HN, After selling my company to a big tech firm and spending a few years there, I finally had the chance to take a break and spend time with my 2-year-old. Watching him grow has…

As a ruby developer who had to move to python for its data science support, it’s very nice to see that people help Ruby to evolve into this direction. Ruby is a beautiful language …