Find out what an LLM system can actually do, then keep the evidence.
START HERE · FIRST RUN · OUTPUT · LICENSING TERMS
SHARE THIS ↗
What it does.
Capability claims are cheap. This review finds what the system can actually use, tests the useful parts, and leaves a reusable baseline so you don't have to figure it all out again later.
Use or inspect the current artifact on the full TOYS page, or open its current acquisition link.