Claude 3.5 Sonnet Changed. My System Prompt Stopped Working. Here's What I Learned.

I've been building with Claude APIs since early 2025. Last month, I noticed something strange: my carefully tuned system prompt stopped producing the outputs I expected. The format was slightly off. The tone shifted. My downstream parsing started failing intermittently. Anthropic hadn't announced any changes to claude-3-5-sonnet-20241022. My code was identical. But the model was behaving differently. This article is what I learned from that experience - and what I now do to catch this kind of drift automatically. What happened I was using Claude for a structured data extraction task.