LAB

Experiments that do not need permission to be useful.

Benchmarks, prototypes, tiny utilities, comparisons and things that may never become a polished product.

LAB NOTE / 01

Graph-aware coding context

The experiment compares the same repository-understanding task with and without graph-derived context. The useful question is not whether a graph looks impressive, but whether it helps an agent find the right files, boundaries and request path with less wandering.

LAB NOTE / 02

Model routing tests

I test providers as infrastructure rather than a model list: availability, real free quota, authentication friction, endpoint compatibility, uptime and what happens when the preferred route disappears.

LAB NOTE / 03

Agent harness benchmarks

Benchmarks use intentionally broken projects so an agent has to discover issues, reason about them, make repairs and prove the result with tests. Token usage and failure modes matter as much as a final “success”.

LAB NOTE / 04

Tiny developer tools

Some ideas are useful long before they deserve a roadmap. This is where small utilities, prototypes and one-purpose helpers get to exist without pretending to be products.

LAB NOTE / 05

AI product trials

The test starts from a task, not a feature checklist. If a product claims to build, reason, automate or save time, I want to see what survives contact with an actual workflow.

LAB NOTE / 06

Useful dead ends

Not every prototype deserves continuation. The useful part is recording why it stopped: weak reliability, bad ergonomics, duplicated value, cost, or simply failing the “would I keep using this?” test.