Discussions

Hey everyone, we're currently moving some of our legacy QA flows to AI agents. It’s efficient, but the non-deterministic nature of LLMs is a headache for regression.

I’ve been looking into generative ai testing challenges and found this breakdown quite spot on for our case: https://testomat.io/blog/challenges-of-generative-ai-for-software-testing/

Is anyone else here using specific frameworks to validate AI outputs, or are you still relying on manual spot checks?