Gardwyn

Evaluated AI engineering

Every high-stakes AI needs a guardian.

Gardwyn builds grounded, evaluated, auditable AI, engineered so the model never owns the final call.

Live safety system recorded · verified in CI 2026-06-03
domain real-emergency safety · AI-in-the-loop
https://mike-e-log.github.io/gg-tank-watch-method/eval-summary.json aa6c4869b0b6909c79dd6609f611bd260fbfb29453f36204c61048cfe1fb3efc
AI owns the final verdict no
View the live demo →

Receipts