Content filtering ensures that AI generated content aligns with specific guidelines and policies. It helps detect and prevent the input of harmful content via prompts and generation of inappropriate or offensive content. In Azure Open AI, content filtering capabilities are provided through Azure AI Content Safety. You can customize content filters in Azure Open AI models to align with your application's guidelines and mitigate potential risks associated with generated content.


Level 3 and 4 startups: If you have not done so, verify your domain and business before applying for content filtering modification access via the links below. 


Startups that are on Level 2 and below: log in to Founders Hub to complete your remaining tasks to level up, verifying your domain and business.


Links for requesting access to content filtering modification:

Azure AI  Custom Neural Voice and Custom Avatar Limited Access Review

Azure AI Vision Face API Recognition Limited Access Review

Azure OpenAI Limited Access Review:  Modified Content Filtering

Azure OpenAI Limited Access Review: Modified Abuse Monitoring