Azure AI Content Safety vs. KYC Portal

Azure AI Content Safety is used for our comment analysis red flag comment process to separate most vulgar, unparlimentary words used in comments and comments which is not safe. Also, the comment contains sexuality, harassment, terrorism, and unwanted content, and things to protect and store in our PostgreSQL pgAdmin database and send as a report to clients for the product safety, and not to bring it to the frontend.

Incentivized

• Azure AI Content Safety correctly finds the unparlimentary words maximum.
• Azure AI Content Safety endpoint and api is easy to create from Azure portal and integrate with our code
• Azure AI Content Safety can do things which Azure AI Foundry model can't do

Incentivized

• Azure AI Content Safety model is very costly that should be reduced
• Azure AI Content Safety sometimes, very few time couldn't handle most vulger contents that should be trained to model
• Azure AI Content Safety metrics and scalability is sometime not politely visible, which should be improved

Incentivized

I have given 10 rating to Azure AI Content Safety because it meets our requirements and actually what we needed during that time to prevent the comments which contains vulgar content. No other model works good properly compared to the Azure AI Content Safety model. We have 20 lakhs comments other models didn't work for even half of it but 75% covered by Azure AI Content Safety.

Incentivized

Azure OpenAI Service based models like Azure OpenAI 4o models, Azure OpenAI 4o mini models and even omni models don't work properly compared to Azure OpenAI Content safety model for comment analysis of unparlimentary words protection. Also, ChatGPT OpenAI models also did the same, and the accuracy was low and errors were created. So Azure AI Content Safety stacks up against these two and so that we choose Azure AI Content Safety over others.

Incentivized

• One time it cost 7000 US Dollars when we ran to test, which is very costly, then we connected with the Azure team and sorted it out and got back 4000 US Dollars. This should not happen
• Azure AI Content Safety helped to find red flagged comments for lakhs of comments for our analysis
• Azure AI Content Safety prevents those comments in our product frontend and store that as report helps us a lot.

Incentivized