A page that stays open for residents' questions while the pile-ons are handled
Clarify is social media comment moderation for local councils and community organisations. It reads every comment on your Facebook, Instagram, TikTok and Threads pages, sorts the residents' questions from the abuse and the bot herds, drafts replies in the council's voice for your communications team to approve, and logs anything that crosses into a threat with the evidence a police report needs. Your page stays a public forum; your staff stop reading everything to find the one question that matters.
7-day free trial on every plan · hosted in Australia · cancel anytime
Read the transcript
The comments section. One of the most hostile environments on Earth. Here, beneath a post about a new footpath, life is abundant. This is the Resign Bird. It has only one call. It will make it anywhere. Footpaths. Christmas greetings. A photo of a dog. The Bot Herd moves as one. Because it is one. Sixteen accounts. One phone. Born last Tuesday. After dark, the Keyboard Warrior emerges. Territorial. Tireless. It knows where your office is. It has found your children's school. This is not a mating display. In the wild, this is called a crime. And buried beneath it all, the rarest creature of all. A genuine question. Shy. Polite. Almost never answered. Every day, one brave staffer must read all of it. Or at least, they used to. But a new species has arrived. Clarify. It reads every comment first. The Resign Birds are sorted. The Herd is exposed. The Warrior's threats are logged, screenshotted, and built into a case for police. In the wild, this is called consequences. And the genuine question finally gets an answer. One you approve. The comments section. Still wild. Now under control. Clarify.
What a council communications team is up against
- Every post attracts the same crowd. A footpath, a Christmas greeting, a photo of a dog: the same accounts arrive with the same demand to resign.
- The page has to stay open. Closing comments is not an option for a public body, so the abuse and the genuine questions live in the same thread.
- Someone reads all of it. Usually one person, often after hours, and it is the part of the job nobody applied for.
- A threat is not a complaint. When a commenter knows where the mayor's office is, or a councillor's kids' school, the team needs evidence, not a screenshot on someone's phone.
What Clarify does for a council's pages
Reads every comment first
Each comment is sorted as a threat, bullying, a slur, spam, misinformation, a genuine question or a legitimate comment, with a confidence score and the reasoning. The AI judges it against your page type and community guidelines, so a heated comment about a road project is treated as what it is: someone who cares about roads.
Drafts the answer, you approve it
For a genuine question, one tap drafts a reply in the council's voice. A team member checks it and, if your workflow needs it, sends it to a manager for approval before anything is posted. Every reply is a person's decision.
Keeps the record
A threat goes to the log with the comment text, the account, the post and the timestamp, Clarify's own record that a later deletion cannot erase, and can be built into a case with a downloadable report for police. Hidden comments are hidden with the platform's own hide, never deleted, and the activity log shows who did what.
Approvals that fit a public body
Councils rarely let one person post on their own. Clarify's reviews and approvals let the communications officer draft a reply or a post and the manager approve it, from the same screen, with the history kept. Team members see only what their role allows.
Posts go out to every connected platform from one calendar, so the flood warning or the works notice lands on Facebook, Instagram, TikTok and Threads at the same time.
Clearing the backlog after a bad weekend
Post moderation shows one card per post with how many comments still need review and how many threats it has, threats first. Work through the posts one at a time, hide or reply in bulk when a thread has gone feral, and mark each post moderated. A post with an unreviewed threat cannot be marked done until someone has looked at it.
Also for the volunteers
- Community groups and associations, run by people who cannot watch the page all day and should not have to read the abuse when they do.
- Libraries, galleries and venues, whose pages are half events calendar and half complaints desk.
- Regional and rural councils, where the commenter and the councillor are likely to meet at the supermarket, so nothing is deleted and every action can be undone.
- Hosted in Australia, with a human in the loop, always.
Frequently asked questions
Can a council use AI moderation without censoring residents?
Yes. Clarify hides with the platform's own hide, which leaves the comment visible to its author and their friends and deletes nothing. By default it hides nothing on its own; a person decides. Auto-hide is opt-in, limited to the categories you choose at 90% confidence or above, and every automatic hide can be undone in one click.
Does it post replies without approval?
No. Clarify drafts a reply when someone asks it to, in the voice you have set, and a person checks and approves it. If your workflow needs a second pair of eyes, reviews and approvals route the reply to a manager before it is posted.
How does it handle threats against councillors or staff?
A threat is logged with the comment text, the account, the post, the timestamp and the AI's assessment, a record Clarify keeps even if the comment is later deleted, and can be built into a case with related comments and accounts. The case report can be downloaded and handed to police. Clarify itself never contacts police or eSafety; that stays your decision.
Can several staff share one workspace?
Yes. Starter includes one team member, Pro five and Agency unlimited, each with a role that controls what they can see and do, and an activity log records who did what.
Is it suitable for a small community group?
Yes. Connect the group's pages, switch on the morning brief, and the volunteer who runs the page reads a short summary instead of the whole thread. Everything is hosted in Australia.
Read how it works, step by step
- The Social StreamThe Social Stream is where most moderation happens. Every comment across your connected socials lands here, already sorted into a category by the AI.
- Replying to commentsClarify can draft replies for you, but a reply never reaches the platform without two deliberate human steps: approving the draft, then posting it.
- Reviews and approvalsSome things deserve a second pair of eyes before they go out in your name. Reviews is Clarify's approval queue: a team member drafts a reply or a post and…
- Post ModerationPost Moderation gives you a post-by-post way to clear your backlog, instead of wading through one giant list of comments.
- The Threat LogThe Threat Log is the permanent record of every comment classified as a threat, organised by the account that made it.
- Media ListeningYour team already watches your own Page all day. Media Listening watches the rest of the internet for you, so a story about you in the news does not slip past.
Pricing
Moderation, replies with approvals, post moderation and the threat log are in every plan; media listening and more team seats start on Pro. Prices in Australian dollars; every plan starts with a 7-day free trial, and paying yearly gives two months free.
More from Clarify
- Threat monitoring and reportingClarify watches the comments on your own Facebook, Instagram, TikTok and Threads pages for threats, preserves the evidence, and builds police and eSafety Commissioner-ready reports.
- Replies in your voiceClarify drafts replies to the comments on your Facebook, Instagram, TikTok and Threads pages in your own voice, checks the facts on the web, and posts nothing until a person approves it.
- Comment moderationClarify sorts every comment on your pages as a threat, abuse, spam, misinformation, a question or fine, hides the clear-cut cases if you switch that on, and keeps every decision reversible.
- Media monitoringClarify watches Google News, GDELT and the outlets you add for mentions of you about once an hour, confirms each story is really about you, summarises it and scores its tone.
- Publishing with approvalsClarify schedules posts to Facebook, Instagram, TikTok and Threads from one calendar with your diary beside it, drafts them in your voice, and routes every post through an approval queue.
- MPs and candidatesClarify reads every comment on an MP's or candidate's Facebook, Instagram, TikTok and Threads pages, hides abuse, logs threats for police and drafts replies to constituents that staff approve.
- Small businessClarify reads and sorts the comments on a small business's pages, drafts replies in the owner's voice, hides scams and spam, and schedules posts to every platform from one calendar.
- Sporting clubs, parties and peak bodiesClarify HQ lets a club, party or peak body see when one account is targeting several of its members across their own pages, and work referred cases together. Free for organisations.
- AthletesClarify reads an athlete's comments before they do, hides abuse the moment it lands, logs threats with evidence, and puts a kind word from a real supporter in every morning brief.
- Creators and influencersClarify sorts a creator's Instagram, TikTok, Threads and Facebook comments, hides spam and abuse, mutes fake accounts, logs threats, and drafts replies to real questions in the creator's voice.
- Everything Clarify does, on one pageClarify monitors the comments on your Facebook, Instagram, TikTok and Threads pages for threats, abuse and bot campaigns, and drafts replies your team approves. Australian-hosted, from A$75 a month.