My workflow “Benchmark Content Safety Guardrails with Automated Test Suite & Reports” is now officially live:
It runs 36 safety test cases (PII, NSFW, jailbreak attempts, unsafe URLs, etc.), scores moderation performance (accuracy, precision, recall, F1), and sends a full HTML report, perfect for anyone working with AI governance, content moderation, or compliance testing.
This is my second approved template, one more until verified creator status.
If you try it, I’d love your feedback, and feel free to share it with anyone working on AI safety, LLM validation, or automation testing