Zod + LLMs: How to Validate AI Responses Without Losing Your Mind

You ask an LLM a carefully crafted question with a system prompt demanding JSON output. You get back a beautifully formatted response wrapped in triple backticks, prefixed with "Here's the JSON you requested:", and trailing with "Let me know if you need any changes!" The actual JSON is buried somewhere in the middle. Sometimes it's valid. Sometimes it's not. This is the fundamental challenge of building tools on top of LLMs: they're probabilistic text generators, not API endpoints. And if you're