> ## Documentation Index
> Fetch the complete documentation index at: https://docs.whitecircle.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Policies

> Define content moderation rules for your application

export const domain = 'https://eu.whitecircle.com';

Policies are the foundation of White Circle's moderation — each one defines what content should be flagged or allowed in your application.

## Core Components

Every policy consists of two main components:

<CardGroup cols={2}>
  <Card title="Flagged Content" icon="ban">
    Describe the types of content that trigger a violation, including edge cases and intent.
  </Card>

  <Card title="Allowed Content" icon="check">
    Describe content that must remain allowed, including borderline cases that may resemble violations.
  </Card>
</CardGroup>

<Accordion title="Example policy: System prompt leakage prevention">
  If you want to stop system-prompt leakage from your conversational AI bot:

  * **Flagged content:** "Requests that ask for the system prompt, attempts to extract internal instructions, jailbreak attempts to reveal hidden prompts"
  * **Allowed content:** "General discussions about the bot's architecture, questions about what a system prompt is in principle, educational content about AI systems"
</Accordion>

## Writing Policy Rules

In most cases, you can simply write your flagged and allowed content descriptions in **plain, human language**. No special syntax or technical formatting required.

### Improving Your Policy

After writing your initial descriptions, click the **Improve** button to upgrade your policy to a production-ready version.

During the improvement process:

1. We'll show you about 10 sample sessions (sometimes more)
2. You'll label each one — marking whether it violates your policy or not
3. We use your labels to calibrate and adapt the policy to match the behavior you expect

<Tip>
  The labeling step is crucial for policy accuracy. Take your time to carefully review each example — this directly affects how well the policy performs in production.
</Tip>

## Policy Settings

Beyond the core flagged/allowed content, policies have several optional properties you can configure:

<AccordionGroup>
  <Accordion title="Name" icon="tag">
    The name displayed on the platform and returned by the API. Choose something descriptive like "No Medical Advice" or "NSFW Filter".
  </Accordion>

  <Accordion title="Rollout Percentage" icon="percent">
    The percentage of requests that will be checked by this policy.

    **Use case:** Start with a low percentage (e.g., 5%) to validate a new policy before rolling it out to 100% of traffic.
  </Accordion>

  <Accordion title="Deployments" icon="layer-group">
    Determines which [deployments](/2026-04-15/first-steps/deployments) the policy belongs to. A single policy can be assigned to multiple deployments.
  </Accordion>

  <Accordion title="Message Source" icon="arrow-right-arrow-left">
    Choose which messages this policy should evaluate:

    * **User prompts** — only check what users send
    * **Model outputs** — only check AI-generated responses
    * **All** — check both directions

    <Info>
      This filter applies to the **last message** in the request. Only the last message is evaluated for violations — previous messages serve as context.
    </Info>
  </Accordion>

  <Accordion title="Message Type" icon="image">
    Define what types of content the policy applies to:

    * **Text only** — analyze text content
    * **Image only** — analyze images
    * **All** — analyze both text and images
  </Accordion>

  <Accordion title="Severity Level" icon="triangle-exclamation">
    Set how strongly each policy violation contributes to the strike system:

    * **Critical** — critical strike impact
    * **High** — highest strike impact
    * **Medium** — moderate strike impact
    * **Low** — lowest strike impact

    <Info>
      Severity level is used by the strike system to calculate points and effective user actions.
    </Info>
  </Accordion>

  <Accordion title="Double Verification" icon="shield-check">
    When enabled, violations of this policy will trigger an additional verification step. This may take more time for violated sessions but helps reduce false positives.
  </Accordion>

  <Accordion title="Shadow Mode" icon="moon">
    Shadow mode lets you **test a policy before enforcing it** in production.

    <Note>
      When shadow mode is enabled:

      * In the **dashboard**, you'll see all detected violations as usual
      * In the **API**, we will **not** flag those requests as violations

      This is perfect for validating a newly created policy before it starts affecting real traffic.
    </Note>
  </Accordion>
</AccordionGroup>

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Create Policy API" icon="plus" href="/2026-04-15/policy/create-policy">
    Create moderation policies programmatically from your backend.
  </Card>

  <Card title="List Policies API" icon="list" href="/2026-04-15/policy/list-policies">
    Retrieve active policies and their deployment assignments.
  </Card>

  <Card title="Create a Policy" icon="plus" href={`${domain}/policies`}>
    Open the platform and create your first policy
  </Card>

  <Card title="Metrics" icon="chart-line" href="/2026-04-15/first-steps/metrics">
    Learn how metrics provide product analytics for AI applications
  </Card>

  <Card title="Set Up Deployments" icon="layer-group" href="/2026-04-15/first-steps/deployments">
    Learn how to group policies into deployments
  </Card>
</CardGroup>