Every team shipping an LLM feature eventually hits the same wall: the thing you built is non-deterministic, and your whole testing culture assumes it isn't. assertEqual(output, expected) is meaningless when the output is a paragraph of generated prose that will be slightly different next time. ...
Source: [Dev.to](https://dev.to/amirmarcel/you-cant-unit-test-an-llm-heres-what-i-built-instead-m6g)