You ask an AI a question and it answers with total confidence. Most of the time, a confidently wrong answer is just an annoyance. But what if the question is medical, and there's a real patient on the other end? In that world, a hallucination isn't a bug, it's a patient-safety event. Sumit Gundawar is a London-based software engineer who builds the clinical platform for a UK longevity and aesthetic-medicine clinic, and his whole argument is that in high-stakes AI, the model is the easy part. Earning trust is the real engineering. We dig into grounding, refusal logic, human-in-the-loop design, and the messy frontier of longevity and biohacking, plus a live demo of an assistant that refuses to answer when it can't back up the claim. Let's get into it.

Coding agents have gotten really good at one kind of work. You scope a feature, edit some files, run the tests, ship it. It all happens on disk. But that is not how data work feels. You load something, you look at it, you run a cell, you watch how it responds, and you decide the next move from whatever is sitting in memory. And until now, your agent couldn't see any of that. It only saw the files. Never the live state.

This episode, that wall comes down. marimo pair drops a coding agent right inside a running notebook, with full access to every variable Python is holding in memory. The notebook becomes a shared canvas. You point, it runs the code. You tell it to zoom in on the Picasso paintings, and the chart just updates. No MCP tools to wire up, no schema to describe. Just Python, and an agent that can finally see what you see. Trevor Manz is back to walk us through it.