Prompt Content
Create 3-5 synthetic test cases, each containing a 'media_url', 'policy_doc', and 'context' that represent a clear policy violation (e.g., unauthorized deepfake, copyright infringement). Run these through your implemented system and analyze the output, focusing on the 'violation_detected', 'violation_type', and 'reasoning' fields. Document any false positives or negatives.
Related Prompts
Explore similar prompts from our community
Usage Tips
Copy the prompt and paste it into your preferred AI tool
Customize the prompt by replacing placeholder values with your specific requirements
For best results, provide clear context and examples when using this prompt