# Agentic AI Governance

<figure><img src="/files/ukDvv0Nk9t6n7uPAW7gM" alt=""><figcaption></figcaption></figure>

<h2 align="center">Coming VERY Soon to Keeper EPM!</h2>

#### Agentic Access Policy JSON Example

{% code overflow="wrap" %}

```json
{
  "PolicyId": "local-test-agentic-access-operator-approval-any-app-ai50-001",
  "PolicyName": "LOCAL TEST – AgenticAccess OPERATORAPPROVAL for any app with AI ≥ 50%",
  "PolicyType": "AgenticAccess",
  "Status": "enabled",
  "Actions": {
    "OnSuccess": { "Controls": ["OPERATORAPPROVAL"] },
    "OnFailure": { "Command": "deny" }
  },
  "NotificationMessage": "Local test – any application with high AI likelihood requires operator approval (agentic access).",
  "NotificationRequiresAcknowledgement": false,
  "RiskLevel": null,
  "Operator": "And",
  "Rules": [
    {
      "RuleName": "UserCheck",
      "ErrorMessage": "User not in policy",
      "RuleExpressionType": "BuiltInAction",
      "Expression": "CheckUser()"
    },
    {
      "RuleName": "ApplicationCheck",
      "ErrorMessage": "Application not in policy",
      "RuleExpressionType": "BuiltInAction",
      "Expression": "CheckFile(false)"
    }
  ],
  "UserCheck": ["*"],
  "MachineCheck": ["*"],
  "ApplicationCheck": ["*"],
  "DayCheck": [],
  "DateCheck": [],
  "TimeCheck": [],
  "CertificationCheck": [],
  "Extension": {
    "pendingControlsJobId": "agentic-policy-controls",
    "agenticOverlay": true,
    "minAiLikelihoodPercent": 50,
    "grantDurationOptions": [60, 240]
  }
}
```

{% endcode %}

{% hint style="info" %}
If `grantDurationOptions` is omitted, the grant will only be extended for the immediate request.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.keeper.io/keeperpam/endpoint-privilege-manager/policies/policy-types/agentic-ai-governance.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.