ml_predict_change_risk

What ml_predict_change_risk does on NowAIKit — ServiceNow AI Toolkit

AI agents call ml_predict_change_risk to retrieve information from NowAIKit — ServiceNow AI Toolkit without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why ml_predict_change_risk is rated Low

This tool retrieves ML-based predictions about change risk as metadata/intelligence. It does not execute changes, modify records, delete data, or commit financial obligations. The prediction itself is informational and advisory in nature. Misuse would have minimal blast radius — an incorrect risk prediction is output data that humans must still approve before any actual change executes.

From the tool's definition Tool description states it 'Predict[s] the risk level' using 'historical ML analysis' — a read-only query operation that analyzes and returns risk predictions without modifying any data or triggering external actions.

The rule that runs ml_predict_change_risk safely

PolicyLayer is an MCP gateway: it sits between your AI agents and NowAIKit — ServiceNow AI Toolkit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ml_predict_change_risk, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ml_predict_change_risk": {}
  }
}

Questions about ml_predict_change_risk