> For the complete documentation index, see [llms.txt](https://support.ariglad.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://support.ariglad.com/article-approvals/how-to-review-and-approve-ariglad-suggestions.md).

# How To: Review and Approve Ariglad Suggestions

Ariglad analyzes your support tickets and automatically generates suggestions for your knowledge base — including edits to existing articles and drafts for new ones. This guide explains how to review those suggestions and publish the ones that look good.

***

**1. Go to the Approvals Page**

Head to [**ai.ariglad.com/knowledge\_base/approvals/resource**](https://ai.ariglad.com/knowledge_base/approvals/resource).

You'll see a list of pending suggestions waiting for your review. Ariglad takes 2–3 days after setup to generate your first suggestions.

***

**2. Understand the Suggestion Types**

Each suggestion falls into one of two categories:

* **Update** — a proposed edit to an existing article, based on gaps or inaccuracies identified in your support tickets.
* **New Article** — a full article draft for a topic not yet covered in your knowledge base.
* **Merge** — a proposed consolidation of multiple existing articles into a single, unified article.
* **Instructions** — a set of proposed changes based on a custom instruction you've defined in [Instructions for your AI writer](https://support.ariglad.com/interactive-modes/instructions-for-your-ai-writer).

***

**3. Review a Suggestion**

Click on any suggestion to open it. You'll see the proposed content alongside the context that triggered it.

Read through the suggestion and decide whether it accurately reflects what your customers need.

***

**4. Approve or Reject**

Once you've reviewed the suggestion:

* Click **Approve** to publish it to your knowledge base.
* Click **Reject** to dismiss it — it will be removed from your queue.

Approved changes go live immediately and are pushed to your connected knowledge base.

***

**Tip**

Use the filters at the top of the Approvals page to sort by suggestion type, brand, or category — useful if you're working through a large backlog and want to prioritize a specific area.


---

# 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:

```
GET https://support.ariglad.com/article-approvals/how-to-review-and-approve-ariglad-suggestions.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.