Bryan Falkowski

Work

Papers, projects and notes on evaluating AI and building with coding agents. Most of it has code you can run.

LinkedIn GitHub Email

Papers and primers

Projects

The Building 58 room with session labels

Building58

A building of 3D loft rooms where Claude Code sessions work as a squad.

Walk in

In progress

Exhibit

Decides what evidence a pull request needs, checks it, and learns its rules from bugs that got through. Built by a Building 58 room.

Code

Eval Run Validity Gate

Checks whether an eval run is valid before its score is trusted.

Code

Evaluation-Driven Design Platform

A deployable system for building, testing and improving AI agents. Room B uses it as a new user would.

Code

Browser Agent Dashboard

Compares a purpose-built decision model with a Claude agent on the same browser test.

Code

LLM Evaluation Service Stack

A containerized service for running LLM evaluation jobs, with a console and Kubernetes deployment.

Code

Notes

Stories

Short story and short film

Doctor Bones

A short story inspired by Player Piano, then a 3D kitchen world and a first-draft film made in one day with AI tools.

Read the story

Films

Building 58 trailers

The people edition and the robot edition, each in 3D and realistic versions.

Watch