ml_train_change_risk

What ml_train_change_risk does on NowAIKit — ServiceNow AI Toolkit

AI agents invoke ml_train_change_risk to trigger actions in NowAIKit — ServiceNow AI Toolkit. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why ml_train_change_risk is rated High

Although labeled '[Write]' in the description, training an ML model is not merely creating or modifying data reversibly; it executes a complex computational operation whose effects on system state and model behavior depend on the training data and parameters. This is an Execute category action because it runs an external operation (ML training) whose consequences are not simple data mutations.

From the tool's definition Tool description states 'Trigger training of the change risk prediction ML model' — the word 'trigger' indicates initiation of an ML training operation, which is a computational process with external effects (model state changes, resource consumption, system…

The rule that runs ml_train_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_train_change_risk, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ml_train_change_risk": {
      "limits": [
        {
          "counter": "ml_train_change_risk_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about ml_train_change_risk