Proof-of-Execution: verifying what AI agents actually execute

I’ve been working on a protocol called Proof-of-Execution (PoE). The idea is simple: AI agents today are evaluated mostly on their outputs, but outputs can be correct even if the agent didn’t actually perform the work. PoE introduces execution traces that can be verified to provide evidence of how the agent completed the task. It’s designed for multi-agent systems and agent infrastructure. Curious how others think about verification in autonomous agent systems. I can share the repo if anyone is interested.