> For the complete documentation index, see [llms.txt](https://help.impact.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.impact.com/brand/what-would-you-like-to-learn-about/creator-program/recruit-creators/creator-content-check/create-a-creator-content-check-policy.md).

# Create a Creator Content Check Policy

*Creator Content Check* reviews a creator's recent content against standards you set, so you can decide whether they're a good fit for your brand before you partner with them. You need to create a policy before you can add any creators.

{% hint style="warning" %}
This feature is currently in closed beta and is not available to all brands.
{% endhint %}

## Tips for setting up your policy

* **Start broad, then narrow down.** Selecting all brand safety terms on your first policy gives you a baseline. Refine once you've seen what a few checks return.
* **Keep custom keywords specific.** Product names, campaign hashtags, and named topics work better than general words, which tend to flag content that isn't a real concern.
* **Match the date range to the decision.** 6 months suits a long-term partnership; 1 or 2 months is usually enough for a short, one-off campaign.
* **Use separate policies for different standards.** Rather than editing one policy repeatedly, create a policy per campaign or per risk threshold.

## Create a policy

1. From the left navigation bar, select ![](https://4048883401-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwMLlMoFBtKJa8ptd3zaw%2Fuploads%2FLGBlwxuVWsrxNsjYUMjf%2Fdiscover-v2%20\(1\).svg?alt=media\&token=8a0e56eb-ff89-4046-8e72-ad2b503f8bf9) **\[Discover] →** [**Creator Content Check**](https://app.impact.com/secure/advertiser/discover/fr/content-safety/policies.ihtml).
2. Start a new policy:
   * If this is your first policy, select **Set Up Creator Content Check**.
   * Otherwise, in the upper-right corner, select **New Policy**.
3. Enter a **Policy Name**.
4. From the ![](https://4048883401-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwMLlMoFBtKJa8ptd3zaw%2Fuploads%2Fgit-blob-c2cb550b55c51ea1eeff0acbd6f437a03b621a2c%2F60d033ae8a04c14498d5229c3c0160ac05feea7f605dbd770741793c900469f0.svg?alt=media) **\[Drop-down menu]** in the *Content Age* section, select a **Content age range**. This sets how far back the check reaches into each creator's content history. You can check as far as 6 months into a creator's history.
5. In the *Keywords* section, select a **Brand safety term** you want to check for.
   * You can select more than one term, or **Select All** to include all of them. Refer to the *Brand safety terms reference* below.

<details>

<summary>Brand safety terms reference</summary>

| Term                     | Description                                                                                                                                                            |
| ------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Violence                 | Content depicting or promoting physical harm, weapons, graphic injury, or violent acts.                                                                                |
| Substances               | Content referencing illegal drug use, drug paraphernalia, or excessive alcohol or tobacco use.                                                                         |
| Sexual Indecent Content  | Content containing nudity, sexually explicit material, or sexually suggestive imagery or language.                                                                     |
| Hate Speech & Aggression | Content that attacks, demeans, or incites hostility toward individuals or groups based on protected characteristics, or that includes threatening or abusive language. |
| Language Toxicity        | Content containing profanity, slurs, or generally offensive or inflammatory language.                                                                                  |

</details>

6. Optionally, you can enter any additional *Custom keywords* you don't want associated with your brand, e.g., a rival product name or a topic that clashes with your brand voice.
   * Separate multiple keywords with commas, or select **Enter** after inserting each keyword.
7. Select **Save**.
   * Your policy is created with the status *No creators added*. [Add creators](/brand/what-would-you-like-to-learn-about/creator-program/recruit-creators/creator-content-check/add-creators-to-your-creator-content-check.md) to it to run your first check.

<div data-with-frame="true"><figure><img src="https://4048883401-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwMLlMoFBtKJa8ptd3zaw%2Fuploads%2FMmwDzE196zSfgbshkYxP%2FScreenshot%202026-08-18%20at%2014.44.11.png?alt=media&amp;token=7b0b8f55-c2b2-4d20-b5ee-0d4fd3291c6b" alt="" width="563"><figcaption></figcaption></figure></div>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://help.impact.com/brand/what-would-you-like-to-learn-about/creator-program/recruit-creators/creator-content-check/create-a-creator-content-check-policy.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.
