Tag
#LLM ops
2 pieces filed under “LLM ops”.
AI · 30 July 2026 · 11 min
Swapping the model without breaking the product
Model migrations without breaking the product: shadow runs, eval-gated cutovers, tone and format regression diffs, and rollback plans for behaviour you can't unit test.
LLM opsmigrationevals
AI · 7 Oct 2025 · 9 minEvals before features: how we measure LLM quality
How we build evaluation harnesses for LLM features: golden datasets, rubric graders, human review lanes and regression tracking that stakeholders can read.
LLM evaluationAI qualitygolden datasets