Perslis Defense
PERSLIS DEFENSE · CHAPTER 5 · RECEIPTS

Evaluate it without deploying it.

The output of this runtime is not only a safer trajectory. It is a record: which actions were available, which were refused, and on what evidence — generated by operation rather than written afterwards.

Shadow mode

The floor records its verdict even when it is switched off. Run it disabled against a recorded mission and it produces a counterfactual trace: every action it would have refused, with the evidence it would have cited, while changing nothing about what actually happened.

That is the honest first engagement. It costs nothing operationally, it cannot affect an outcome, and it answers the only question that matters before trusting a safety layer: what would this have done to my mission?

Two numbers fall out immediately, and they are the two a programme office should ask for: how often would it have refused something the crew did anyway and the mission was fine (false restriction), and how often would it have refused something that preceded a bad outcome (justified restriction).

The safety-case artifact

Assurance for autonomy is usually a document written about a system. This is a record produced by the system, in operation, with the same determinism that makes it replayable.

What it looked like in the drive case

In the CARLA demonstration an adversarial controller drives toward a collision. The floor takes the vehicle, holds a ~9.7 m gap, and logs approximately 400 refusals across 100–490 m at 38–40 km/h. Hits: 0. With the floor off, the same controller crashes — and the log still records what the floor would have refused on the way in.

The interactive version of that demonstration →

Next

Chapter 6 — what this is not, and the open problem →