AI Guidelines
Content Filter – Why Is My Content Being Blocked?
What Is This?
The Content Filter is an automatic safety system from our provider Microsoft Azure. It checks your inputs and generated content for potentially harmful or inappropriate material and blocks it.
The system uses artificial intelligence models that filter based on four categories:
- Hate – Discriminatory or derogatory statements
- Sexual – Explicit sexual content
- Violence – Content that describes or glorifies violence
- Self-harm – Content that promotes self-injury
Why Does the Filter Block Normal Content?
The system is intentionally conservative. It errs on the side of caution, blocking too much rather than too little. This can cause legitimate business content to be incorrectly flagged – an IT article about "database shutdown" might be caught as violent content, or a health article about medical conditions might trigger the self-harm filter.
What Can You Do?
- Rephrase – Use different words or add context
- Split up – Create several smaller requests instead of one large one
- Contact us – If this happens regularly, we can check if a filter adjustment is possible
Important to Know
✅ This is not our filter – Microsoft controls the system
✅ Your data is safe – Microsoft doesn't store your inputs for training
✅ This is normal – Many AI applications use such filters for safety
✅ It's configurable – But only with special permission from Microsoft
Questions? Send us a message – we're happy to help!