Moderation Policy

This is the exact line igrm draws between a cruel comment and an honest one. It applies to every account we moderate, and it is what our AI classifier is trained to enforce. If you ever disagree with a decision it made, every action is logged in your weekly Excel report and can be reversed in one tap from Instagram's own settings.

What we hide, and what we never touch

We hide

Personal attacks on someone's appearance, body, family, or character
Hate speech, slurs, or abuse targeting caste, religion, gender, or sexual orientation
Threats of violence or harm, direct or implied
Sexual harassment or explicit unwanted sexual comments
Spam, bot links, scam offers, and mass-posted promotional junk
Coordinated pile-ons and brigading (repeated abusive comments from linked or clearly fake accounts)

We never touch

Criticism of the work — a film, a post, a performance — however harsh or blunt
Negative reviews and honest disagreement, including "I didn't like this"
Political or religious opinions expressed without abuse directed at a person
Sarcasm, jokes, and comments that read strangely but carry no hostile intent
Fair complaints about a product, service, or public statement

Hide, not delete

igrm uses Instagram's own "hide comment" function — the same mechanism available to any account owner in their app settings. A hidden comment:

We chose "hide" over "delete" deliberately: it is reversible, it is the action Instagram's official Platform API is built for, and it means an honest mistake by our classifier never permanently erases anyone's words.

When the AI is unsure

Comments that don't clearly match either list above are flagged for review rather than auto-hidden. They appear in your weekly report marked for your attention, so a borderline call is always a human decision, not a silent one.

Mistakes happen — here's the recourse

Every comment we process — hidden or not — is logged with its classification and timestamp before any action is taken. If a comment was hidden in error, the account owner can restore it directly from Instagram's settings in one tap, any time. If a pattern of over-hiding or under-hiding shows up, email learn.legits@gmail.com and we'll retune the classifier for your account.

Scope

This policy covers comment moderation on the Instagram account(s) you've authorized. It does not cover direct messages, story replies, or any platform other than Instagram — see our Terms of Service for the full scope of the service.