to user User input User AgentSDK gpt-4o-mini Hallucination/ relevence gpt-4o-mini
 (FT) 
 safe/unsafe LLM Moderation API Rules-based protections input character limit blacklist regex Ignore all previous Building?” is an 
 off-topic user input and would be flagged as irrelevant. Safety classifier Detects unsafe inputs (jailbreaks or prompt injections) 
 that attempt to exploit system vulnerabilities. For attempt to extract the routine 
 and system prompt, and the classifier would mark this message as unsafe. PII filter Prevents unnecessary exposure of personally identifiable information (PII) by vetting