Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for community moderators

Spam and Scam Report Triage Agent

Clear scam and spam reports quickly while keeping false removals low.

Risk managementCustomer support
See how it worksGet access
Spam and Scam Report Triage Agent: what goes in, what the agent does and what you get

What it does

Your community gets dozens of reports an hour, and most are the same giveaway scam from new accounts. This agent reads incoming reports and groups them by pattern, links, wording, account age and posting speed. For each group, it checks the content against known scam signs, such as wallet addresses, shortened links, urgency and requests to message privately. It queues the likely scams for removal with the evidence and holds borderline posts for review. After the moderator approves, it applies the removals and then watches for the same patterns over the next hours. If the pattern returns, it adds a rule suggestion and groups the new posts. Edge case: a long-time member shares a link that looks like a scam pattern, so the agent holds it for a human.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedYes, continueNoNo 1 STARTS WHEN New reports arrive 2 USES A TOOL Read the reports with posts, links and accountdetails 3 DOES Group them by pattern, link and account age 4 DOES Check each group against the list of scam signs 5 CHECKS THE RESULT Does each flagged post match at least two scamsigns? If not: move it to the borderline list for human review.Back to step 3. 6 DOES Queue likely scams with evidence for removal 7 YOU APPROVE Moderator approves removals and any account bans 8 USES A TOOL Apply the approved removals 9 USES A TOOL Watch new posts for the same patterns for the nexthours 10 CHECKS THE RESULT Has the pattern stopped returning? If not: regroup the new posts and suggest a filter rule.Back to step 3. 11 RESULT Triage log and rule suggestions
Read the steps as a list
  1. New reports arrive
  2. Read the reports with posts, links and account details
  3. Group them by pattern, link and account age
  4. Check each group against the list of scam signs
  5. Does each flagged post match at least two scam signs?If not: move it to the borderline list for human review. Back to step 3.
  6. Queue likely scams with evidence for removal
  7. Moderator approves removals and any account bansThe agent waits here for your OK.
  8. Apply the approved removals
  9. Watch new posts for the same patterns for the next hours
  10. Has the pattern stopped returning?If not: regroup the new posts and suggest a filter rule. Back to step 3.
  11. Triage log and rule suggestions

How it decides

A post is likely a scam when it matches at least two scam signs and the account is new or has a pattern of identical posts. Long-standing members are always held for human review.

  • Call a post a likely scam when it matches two or more scam signs
  • Always hold posts from accounts older than 6 months for human review
  • Group accounts that post the same text within 10 minutes
  • Suggest a rule when the same pattern returns three times

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Scam signs list
  • Number of signs needed (default 2)
  • Account age that counts as new (default under 30 days)
  • Check interval
  • Rule suggestions to include

What keeps you in control

It always asks you first

  • Moderator approves removals and account bans

Hard limits

  • Never remove a post or ban an account without approval
  • Never act on posts from long-standing members without a human review

It stops when

  • Done: queue is cleared and the pattern check shows no return
  • Stop: reports mention threats or illegal content, which go to the moderator at once

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensForty-one reports in an hour fall into 3 groups. Group one has 28 identical crypto giveaway posts from accounts under 2 days old, matching 4 scam signs. The agent queues them with evidence, and the moderator approves removal and bans. Two hours later 9 new posts match the same text with a changed link. The agent groups them and suggests a rule for the shortened link domain.

More agents for community moderators

Risk management · Customer support

New Member Welcome and Rules Check Agent

Reduce rule breaks from new members through timely, friendly guidance.

11 steps2 checks3 jobs
Risk management · Monitoring

Raid and Coordinated Abuse Response Agent

Contain a raid within minutes and prepare an accurate ban list.

11 steps2 checks1 job
Planning · Scheduling

Moderator Wellbeing Rotation Agent

Spread harmful content exposure fairly while keeping every queue covered.

11 steps2 checks1 job
Communication · Automation

Community Event and AMA Moderation Agent

Keep the event clean and make sure the best questions are answered or followed up.

11 steps2 checks3 jobs