# How to manually configure reactions in Direct Messages

## How to create a direct link to Direct Messages

The link is formatted as `https://ig.me/m/#{your-instagram-username}`. This means that to generate the link, replace `#{your-instagram-username}` with your actual Instagram account username.

{% hint style="warning" %}
The direct link works **ONLY** when opened through the mobile app.

It does not work in a browser!
{% endhint %}

## Set up keyword-based replies in Direct Messages

To set up keyword-based auto-replies in Direct Messages, use blocks with a trigger (**Start block** or **Trigger block**).

For the matching type, choose either **Keyword match** or **Exact match** (recommended options).

<div data-with-frame="true"><figure><img src="/files/j3FTXZ1asfd48ARWh708" alt="" width="563"><figcaption></figcaption></figure></div>

In the **Trigger** field, specify one or more conditions (separated by semicolons) to launch the bot.

In the **"Message text"** field, enter the bot's response that the user will receive. You can also add attachments, buttons, and links.

## How to like the last user message

To like the user's latest message, enter the following function in the "Calculator" field:

**like\_client\_message()**

Then, after going to this block, the user will receive a like for the last message they sent.

<div data-with-frame="true"><figure><img src="/files/Hn1Uom45Mux6Sk7rifVC" alt="" width="563"><figcaption></figcaption></figure></div>

The result:

<div data-with-frame="true"><figure><img src="/files/zXe8fDL90F2ZqtxCH7gW" alt="" width="375"><figcaption></figcaption></figure></div>


---

# Agent Instructions: 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://docs.mavibot.ai/chatbot/messengers/instagram/settings/how-to-manually-configure-reactions-in-direct-messages.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.