> For the complete documentation index, see [llms.txt](https://help.meetmadison.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.meetmadison.ai/social/comments.md).

# Comments

Engaging with comments keeps your audience close, but watching every post is hard. Madison keeps an eye on the comments on your published posts, **drafts a reply for you**, and lets you approve it in a click.

## How it works

Madison watches the comments on **all** your posts, both the ones you published through Madison and ones you posted directly on the platform, so nothing slips through.

When someone comments on one of your posts, Madison writes a draft reply and notifies you. For each one you can:

* **Approve** it to post the reply
* **Edit** the wording first
* **Refine** it
* **Reject** or **delete** it

Madison drafts replies for comments on **Facebook**, **Instagram**, and **LinkedIn**.

{% hint style="info" %}
On LinkedIn, the commenter always shows as "LinkedIn Member" with no name or profile picture. That's a LinkedIn limitation, not something Madison can change.
{% endhint %}

{% hint style="info" %}
Comment replies are available on **Premium** and **Ultimate**. See [Settings → Plan & Billing](/settings/billing.md) to upgrade, or contact us at <support@meetmadison.ai>.
{% endhint %}


---

# 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.meetmadison.ai/social/comments.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.