---
title: Policy Validators
excerpt: ''
deprecated: false
hidden: false
metadata:
  title: ''
  description: ''
  robots: index
next:
  description: ''
---
# What are Policy Validators?

While it's appropriate to steer some behavior through natural language, enforcing **business rules** through natural language can be unreliable.

* Natural language policies are useful when there is a lot of nuance, but they are too imprecise for strict rules.

  <Table align={["left","left"]}>
    <thead>
      <tr>
        <th style={{ textAlign: "left" }}>
          Example
        </th>

        <th style={{ textAlign: "left" }}>
          Optimal Steering Behavior
        </th>
      </tr>
    </thead>

    <tbody>
      <tr>
        <td style={{ textAlign: "left" }}>
          "If the escalation seems important, surface it to the on-call engineer"
        </td>

        <td style={{ textAlign: "left" }}>
          **Natural Language**

          Let the LLM decide if it's important.
        </td>
      </tr>

      <tr>
        <td style={{ textAlign: "left" }}>
          "If the employee is not an FTE, don't show them our FTE benefits"
        </td>

        <td style={{ textAlign: "left" }}>
          **Rules** `

          ```
          employee.status IN ["Contractor", "Contingent"]`
          ```
        </td>
      </tr>
    </tbody>
  </Table>
* Natural language policies can be misunderstood by LLMs, or users might jail break them.
* The more policies you add, the less likely your AI agent will reliably enforce policies ([Lost in the Middle](https://arxiv.org/abs/2307.03172) problem).

Policy Validators enforce & guarantee that rules are **always** respected accurately — no matter how many you add.

Learn more about [our approach to policy validators here](https://www.moveworks.com/us/en/resources/blog/how-policy-validators-help-ai-compliance).

# How do you configure Policy Validators?

We have policies embedded in different parts of our product to provide you control where you need it

* **[Activity Confirmation Policies](/docs/activities#/activity-confirmation-policies)** - enforces user approval before an action in taken.
* **[Slot Validation Policies](/docs/slots#/slot-validation-policy)** - validates input values satisfy constraints
* **[Slot Inference Policies](/docs/slots#/slot-inference-policy)** - decides if the LLM must ask the user for an input.
* **[Conversational Process Decision Policies](/docs/control-flow#/conversation-process-decision-policy)** - controls agentic decision-making with rules

<br />