Praxa makes AI agent actions auditable from proposal to effect
Praxa gives AI agent builders a way to distinguish a proposed action from authorized execution, its verified external effect, and promotion into serving, making each transition testable instead of implicit. Its harness uses deterministic admission, brokered execution, external read-back, and reconciliation; a repository audit passed 1,027/1,027 unit tests and 89/89 Workerd tests. A 12-task Terminal-Bench pilot found no reliability advantage, so the paper supports the architecture, not production gains or security claims.