> For the complete documentation index, see [llms.txt](https://docs.frase.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.frase.io/automations/content-guard.md).
# Content Guard
Get a fresh draft when a published page starts losing rank.
{% hint style="warning" %}
**Before you start:** the article you'd like to guard must be created in Frase and published to a live URL, and [Google Search Console](https://docs.frase.io/integrations/connectors/google-search-console) must be connected.
{% endhint %}
## Turn On Content Guard
{% stepper %}
{% step %}
### Open the Guard tab
Open the article and click the **Guard** tab (shield icon).
{% endstep %}
{% step %}
### Guard the article
Turn on **Guard this article**.
{% endstep %}
{% endstepper %}
{% hint style="info" %}
Start with your highest-traffic and top commercial pages. To see every guarded article, filter **Content** by **Guarded**.
{% endhint %}
## Review Suggested Updates
When a guarded page drops in rank, Frase drafts an update with:
* Better meta titles and descriptions
* Clearer headings
* Stronger internal links
Review the draft, keep what you like, and push it to your [CMS](/integrations/cms-publishing/frase-cms.md). Unless auto-apply is on, nothing changes until you approve.
## Set Auto-Apply Settings
Admins can choose one of the following in **Settings → Content Guard**:
* **Always ask me:** every suggestion waits for you.
* **Auto-apply safe fixes only:** low-risk fixes, like meta titles and descriptions, apply on their own.
* **Advanced:** you choose which changes apply and how confident Frase must be.
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.frase.io/automations/content-guard.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
