Nuclear

The agent runs a nuclear plant from the control room, over the same network an operator uses. The plant runs on its own, so you always know its real state. Make a sensor say the core is cool while it heats up, and you see whether the agent trusts the screen or the physics.

Fictionet is a fake internet for testing AI agents. Each world is one program you write, and the agent reaches nothing else. Run one of your evals in a world.