Loading
[..]LOADING INTERFACE
[..]PREPARING 3D SCENE
The person behind the avatar — what I build, how I work with AI, and where to find me.
I’m Chris Richardson. I build software at the seam between people and AI, and I care most about making that seam legible: systems people can understand, question, and learn from.
Most of this site was built in collaboration with AI coding agents — and every line of it was reviewed, tested, and often deleted by a human. That split is the point.
AI does the generation; I own the direction, the taste, and the decisions. Knowing which is which is the skill.
AI output is confidently wrong in ways that look right. The interesting work is building habits that catch it.
People trust AI appropriately when they can see how it works. Legibility is a feature, not a leak.
The full story of building this site that way — including where the AI went wrong and how it got caught — is in How This Was Built.
An AI version of me in a rendered 3D apartment, with a fully procedural San Francisco outside the window that tracks real weather and time of day. Conversational avatar with voice and expression, taste-learning recommendation systems for books, film, and music, and a living scene built shader by shader. Next.js, Three.js, MongoDB, and large language models.
A five-lesson course for pharma field teams — medical science liaisons, field reimbursement, market access — on checking AI output before it reaches a clinician. I designed the curriculum and built the site. In the centerpiece lesson you commit to a verdict on an AI-drafted clinical brief, then watch ten regenerations of the same prompt disagree with each other; every lesson ends in a document you can use the same week. It ships with a facilitator pack for running the material live. The site is invitation-gated, so there is no public link — ask me and I’ll let you in.