Create RAI Policy
lyzr_rai_create_policyCreate a Responsible-AI guardrail policy to detect toxicity, prompt injection, NSFW content, and banned topics. Adjust thresholds to set the allowed tolerance levels.
Instructions
Create a Responsible-AI guardrail policy (toxicity, prompt-injection, NSFW, banned topics).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"name": "<name>"
},
"name": "lyzr_rai_create_policy"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Policy name | |
| nsfw_check | No | Enable NSFW check | |
| description | No | ||
| banned_topics | No | Topics to block | |
| nsfw_threshold | No | ||
| prompt_injection | No | Enable prompt-injection detection | |
| toxicity_threshold | No | < 1.0 enables the toxicity check at that threshold (1.0 = off) |