I am Vinith Kumar, a Python and AI engineer in Dublin. These are my notes, the working write-ups of the systems I build. Each one takes a real problem, shows the decisions that made it honest, reports the measured result, and ships open source with a demo you can run. No hype, just what I made and what it taught me.
Every one of these is about the same thing, making AI you can actually trust. Open a card to read the full write-up of that project.
A no-code data-science copilot that runs the whole ML workflow from a spreadsheet and refuses to cheat. One scikit-learn engine behind a web console, a LangGraph agent, and an MCP plugin.
Read the post →A support agent that answers what it can prove and hands the risky cases to a human before anything is sent, measured against a plain bot on the cases that cost money and trust.
Read the post →Watching demand forecasts drift the way an SRE watches servers, then turning them into order quantities, measured on 300 real Walmart products.
Read the essay →I care about the parts most people skip, the monitoring, the grounding, the human oversight, and the honest evaluation. A model is easy to build and easy to fool, so the work that interests me is the layer that makes a result trustworthy enough to act on. I am always building toward systems that turn predictions into decisions a business can actually use, and I write each one up here so the thinking is out in the open.
If you work on applied machine learning, agents, or trustworthy AI, I would love to talk.