How to design a strong verifier for AI agent loops
LoopGain decides when an agent loop has converged. It does not decide whether your verifier is right — it trusts the error signal you give it. We measured what happens when that signal has blind spots: 4.5% of our own ‘converged’ code runs failed a fuller test than the loop ran. This is a field guide to building a verifier strong enough to trust at the stop.