29The customer's LLM bill is unsustainable. Cut costs 10x without destroying quality. Walk me through it.▼hardOpenAIMicrosoftGoogle1 replies◆ premium10x doesn't come from one trick. It's multiplicative: routing x caching x prompt diet x batching x distillation. The stacked-levers playbook with rough multipliers, and the eval gate that keeps quality honest.Open full answer →
16How do you size Snowflake warehouses, when do you scale up vs scale out, and how do you keep the bill sane?▼mediumSnowflakeMicrosoftRetool1 replies○ sign inThe question that simulates the actual FDE job: a customer's Snowflake bill just doubled. Scale-up vs scale-out is the easy half, the scoring is on workload isolation, auto-suspend, and proving which knob to turn.Open full answer →
21The pilot succeeded, but the customer says it's 'too expensive to roll out.' Save the deployment without killing the economics.▼hardDatabricksOpenAISnowflake2 replies◆ premium'Too expensive' after a winning pilot is a solvable engineering problem wearing a procurement costume. Here's the diagnose-then-optimize playbook, including the 10x cost levers, that turns it around.Open full answer →
