# 8 September : Instagram AI Comment Automation
📢 New Feature: Instagram AI Comment Automation
We’ve introduced Instagram Comment Intent Classification & Automation to make managing Instagram interactions easier.\
* The system loads your latest 30 posts (or last 60 days) and analyses up to 1000 recent comments.
* Comments are auto classified into categories like *Buying, Support, Spam,* etc.
* Get analytics and insights on comment trends to prioritize engagement.
* Configure the system with your business details and set clear instructions for replies & DMs.
* Two modes available:
* Simulated Mode – Preview AI replies before sending.
* Live Mode – Instantly reply and send DMs on Instagram.
This feature helps you respond faster, stay organized, and boost customer engagement.
Steps to follow:
1\. On the left-hand side, go to settings and click on the IG channel.
2\. Once you are on the IG channel, navigate to the IG posts section and click on Automation Configurations to enable comment automations.
3\. You can view the intent comments (positive or negative comments) and confidence score by clicking on the IG Comments – Intents section.
Example of positive comments – “I like this design.”
Example of negative comment – “Hate this design.”
For example, if an interior design company were to automate IG comments, it could be categorized as follows:
Buying – “Can you share the cost for this kitchen design?”
Support – “I can’t open the link to your catalogue.”
Spam – Irrelevant or promotional comments.
Auto-reply – “Thanks for your interest! We’ll DM you our design packages.”
DM – Send your portfolio link or consultation booking page via DM.
\
\
\
---
# 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://changelog.gallabox.com/september-2025/8-september-instagram-ai-comment-automation.md?ask=
```
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.