Prompt edits and retrieval tweaks accumulate around a frozen model; this shows the alternative running in production — daily distillationTraining a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.Full definition → of production failures into weights, with quality definition as the reward signal and a 96% serving-cost cut.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
