Block harmful content, hide personal info (PII redaction) in replies, and stay-on-topic rules with allowed and blocked topic lists. Advanced settings include prompt injection detection (Off, Standard, Strict), output toxicity filter, content moderation level, hallucination guard, max input tokens, rate limit per user, cooldown seconds, max messages per session, competitor mention rules, PII leakage check on output, and brand tone check.
What safety controls are available?
< 1 min read
- View as Markdown Open this page as plain Markdown (opens in a new tab)
- Open in ChatGPT Ask questions about this page (opens in a new tab)
- Open in Claude Ask questions about this page (opens in a new tab)
- Open in Google AI Studio Ask questions about this page (Google account required) (opens in a new tab)
Found this useful?Add as Preferred Source on Google
Updated on 31/07/2026