Social media threat monitoring, from the first comment to the police report
Clarify monitors every comment on your connected Facebook, Instagram, TikTok and Threads accounts for threats. Each threat is classified as it arrives, recorded with its author, the post and the timestamp, and alerted to your team, and the record survives even if the comment is later deleted. When one crosses the line, Clarify turns the record into a case with a timestamped PDF report ready for the platform, the police or the eSafety Commissioner.
7-day free trial on every plan · hosted in Australia · cancel anytime
How threat monitoring works in Clarify
Connect your pages
Sign in with Meta or TikTok and pick the accounts to protect. Clarify only sees what your page already sees, and it syncs comments on a schedule you set.
Every comment is classified
Each new comment is sorted as a threat, bullying or harassment, a slur, spam or bot activity, misinformation, a genuine question or a legitimate comment, with a confidence score and the AI's reasoning. Threats go straight to the threat log and trigger an alert, in the app and by email, to whoever is on duty.
A person decides
Your team reviews each threat, hides it if needed, tracks the account, or raises a case. Clarify never hides a comment, contacts a platform or reports to anyone on its own.
What does Clarify record about a threat?
Every threat is kept with the account that made it, the comment text, the post it was on, the timestamp, the AI's confidence and reasoning, and whether it has since been hidden or moderated. Threats are grouped by account, so a repeat offender is badged as one, with how many threats they have made and when they were first and last seen.
That record is Clarify's own. A commenter who deletes the comment or a platform that clears a notification does not erase the evidence.
How do I report a threat to the police or the eSafety Commissioner?
Click Raise case on the account. Clarify opens a case at Critical priority with the account and its threats attached, on a board that tracks it from gathering evidence to report submitted to closed. From the case you generate a timestamped PDF report with the comments, their classifications and context, ready to hand to the platform, the police or the eSafety Commissioner.
Every change to a case is recorded with who made it, and evidence attached to an active case is retained even if the commenter asks for their data to be removed, where the law allows.
Can Clarify tell when the accounts are working together?
Yes. Coordination detection looks across your tracked accounts for timing patterns, near-identical phrasing and the same message dropped on many posts, then proposes groups with a suspected coordinator and its reasoning. Open a group to see every member's suspicion score and a combined timeline where comments posted within thirty minutes of each other are badged, so a coordinated wave is obvious.
A group has its own printable dossier, timestamped and marked confidential, and can be raised as a single case. Nothing becomes a record until a person clicks Apply.
What about the ones who keep coming back?
The account tracker is your watch list. Accounts that make threats are tracked automatically, and any commenter can be flagged from the stream. Each profile holds every comment the account has made on your pages, its classification history, flags, behaviour signals, your team's notes and any cases it is attached to. The fiftieth awful comment looks different when you can see the other forty-nine.
For a persistent nuisance who does not warrant a case, mute them for a day, a week, a month or indefinitely. Accounts marked for eSafety reporting stay on your dashboard so they are not forgotten.
Who sees the pattern across many offices?
A party, a council group or an authority can run Clarify HQ, a free organisation portal with a read-only view across every member workspace that chooses to connect. It shows who is taking the most heat, the accounts targeting several members at once, and the cases escalated up for help. Connection is by single-use invitation and the member can revoke it at any time.
Who uses Clarify for threat monitoring
- Members of parliament and ministers' offices, where staff read the worst of the internet every day so the person they protect does not have to.
- Councils and public authorities, whose pages draw threats over decisions they are legally required to make.
- Candidates during a campaign, when the volume spikes and the evidence has to be clean.
- Public figures and the people who manage them, who need a record that holds up, not a folder of screenshots.
Frequently asked questions
What counts as a threat in Clarify?
Clarify classifies a comment as a threat when it threatens violence or harm, and gives each one a confidence score and the AI's reasoning. High-confidence threats land in the threat log and trigger an alert. Whether to act is your team's judgement: as a rule of thumb, a specific threat against a specific person, a stated time or place, or any mention of weapons should go to the police immediately, and the case report gives them a clean, timestamped record.
Does Clarify monitor all of social media, or just my pages?
Clarify monitors the comments on the Facebook, Instagram, TikTok and Threads accounts you connect. It does not scan the whole of social media or private messages. For coverage of the news, Clarify's media listening watches Google News, GDELT and the outlets you add for mentions of you.
Will Clarify report a threat to the police for me?
No. Clarify documents the threat, preserves the evidence and generates the report, and a person on your team decides what to do with it. Clarify never contacts a platform, the police or the eSafety Commissioner on its own.
What happens if the commenter deletes the comment?
Clarify keeps its own record of the comment text, the account that wrote it, the post it was on and the timestamp, so a deletion on the platform does not erase the evidence. Evidence attached to an active case is retained even if the commenter asks for their data to be removed, where the law allows.
How quickly will my team know about a threat?
Clarify syncs your pages on a schedule you set and classifies new comments as they arrive. A threat triggers an alert in the app and, for anyone who has turned it on, by email, so the duty press officer can take email alerts while everyone else watches the bell. The Monday digest also calls out anyone who made threats during the week with no case open yet.
Can Clarify spot a coordinated attack?
Yes. Coordination detection groups accounts that post in the same short windows, use near-identical wording or drop the same message across many posts, names a suspected coordinator with its reasoning, and shows the group's comments on one timeline. Each group can be exported as a dossier or raised as a case.
How much does threat monitoring cost?
The threat log, alerts, the account tracker, coordination groups, cases and reports are included in every Clarify plan. Plans are A$75, A$149 and A$299 a month, each with a 7-day free trial, and Clarify HQ organisation accounts for parties and authorities are free.
Where is the evidence stored?
In Microsoft Azure's Australian region. Data stays in Australia, is encrypted in transit and at rest, and every workspace is isolated from every other. Two-factor authentication is mandatory for every account.
Read how it works, step by step
- The Threat LogThe Threat Log is the permanent record of every comment classified as a threat, organised by the account that made it.
- CasesA case is a folder for an investigation: one account or group, the evidence against them, and the status of any report you've made.
- Coordination GroupsSometimes abuse isn't a collection of individuals; it's a campaign. Coordination Groups is where Clarify identifies clusters of accounts acting together: bot…
- The Account TrackerThe Account Tracker is your watch list: accounts that have been flagged for threats, repeated abuse, suspected fakery, or coordinated behaviour.
- Alerts and the post re-open policyIn Settings > Alerts you choose how you personally hear about events. Each alert type has two toggles: In-app (the bell at the top of the screen) and Email.
Pricing
The threat log, alerts, the account tracker, coordination groups, cases and reports are in every plan. Prices in Australian dollars; every plan starts with a 7-day free trial, and paying yearly gives two months free.
More from Clarify
- 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.
- Councils and community groupsClarify sorts the comments on a council's social pages, drafts replies to residents' questions in the council's voice for staff to approve, and keeps abuse and threats out of the feed.
- 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.