Tag: llm-ops

All the articles with the tag "llm-ops".

• Evaluating voice agent quality at scale

  Sourish Biswas | September 18, 2026

  We improved how our voice agent identifies callers, but a pass/fail metric couldn't see the difference. Here is how we graded thousands of calls with a second model, and what we found when we checked the grader against human review.

• When the model overthinks

  Zhixuan Lai | July 7, 2026

  Sometimes reasoning models get stuck in loops that burn thousands of tokens and produce nothing. Here is how we fixed it.