Viewing profile — wingrammer

That’s an interesting way to frame it. What we kept running into is that even when the agent output itself is correct and admissible, distributed systems behavior can still produce…

Hey I'd love to talk to people using this amazing framework!

Hi HN – I'm the founder of Kybernis. The core problem we’re exploring is that AI agents are non-deterministic systems operating inside deterministic infrastructure. Traditional sys…

AI agents increasingly execute real system actions: issuing refunds, modifying databases, deploying infrastructure, calling external APIs. Because agents retry steps, re-plan tasks…