The most common failures for production agents are behavioral: looping, reasoning leakage, user frustration, and more. Using a frontier model like GPT or Sonnet to judge every turn is too expensive and slow to run at scale.How it works:We use a modern LLM with hybrid attention and remove the decode step. We built an inference engine that lets prefill compute be 99% reused from reflex to reflex, similar in spirit to older 2019-era BERT/HYDRA + older multiple-head techniques.We took the same high-level idea and did the hard work to make it work with a modern architecture and attention. On it, we can run inference in under 30ms and serve the full request in under 90ms. If you run 4 reflexes or 100, the extra overhead is less than 2ms.Why does optimizing this matter?If you’re even a medium-sized startup, you’re dealing with tens of thousands of agent runs and millions of turns. If you want to track things like user frustration rates over time, frontier LLM-as-judge does not scale.I built a...