Skip to main content
Cevro AI is designed to protect player privacy by automatically redacting personally identifiable information (PII) before sending any player data to language models (LLMs). Our proprietary reasoning pipeline ensures that sensitive information remains secure throughout the AI processing workflow.

​
How PII Redaction Works

  1. PII Detection & Redaction: Before data is sent to an LLM, Cevro AI automatically detects and redacts sensitive information such as names, email addresses, phone numbers, and payment details.
  2. AI Response Generation: The redacted message is processed by the AI, ensuring that no identifiable player data is exposed.
  3. PII Reinsertion: After the AI generates a response, Cevro AI seamlessly reinserts the original PII into the message before delivering it to the player.

​
Privacy & Security Commitment

  • Automatic PII Redaction before data reaches the AI model.
  • Secure Processing through Cevro AI’s proprietary reasoning pipeline.
  • Seamless Reinsertion of PII to ensure accurate and personalized responses without compromising security.
This advanced redaction system ensures that player data remains protected while maintaining high-quality AI-generated responses.