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 crisis communications managers

Rumor Tracking and Fact Sheet Agent

Give the manager a verified fact sheet and a clear view of how far the rumor has spread.

Risk managementMarketingPR and communicationsManagement
See how it worksGet access
Rumor Tracking and Fact Sheet Agent: what goes in, what the agent does and what you get

What it does

When a false claim starts to spread, the facts sit in finance, legal and operations while the claim travels faster. The agent tracks where the rumor appears, which accounts amplify it and how quickly it is growing. At the same time it asks the right owners for verified facts and drafts a fact sheet that answers each claim in plain words with a source. It then checks every statement in the sheet against the evidence it received. Anything unverified is held back, and the agent asks the owner for proof. It keeps watching spread after each update to suggest whether to publish, respond to one outlet or keep monitoring. Edge case: half of a claim is true. The sheet must say which half. The manager approves what is published and where.

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 A rumor is flagged 2 USES A TOOL Search social and news for the claim and log eachsource and its reach 3 DOES Split the rumor into separate checkable claims 4 USES A TOOL Ask the fact owners to confirm each claim with arecord 5 DOES Draft a fact sheet answering each claim with itssource 6 CHECKS THE RESULT Is every statement in the sheet backed by aconfirmed record? If not: hold back the statement and ask the owner againfor proof. Back to step 3. 7 YOU APPROVE Manager approves what is published and where 8 USES A TOOL Publish through the approved channels 9 USES A TOOL Re-check spread and sentiment after 2 hours 10 CHECKS THE RESULT Is the rumor still growing? If not: re-run the search, update the claim list and thesheet, and send to the manager again. Back to step 2. 11 RESULT Final summary and monitoring plan
Read the steps as a list
  1. A rumor is flagged
  2. Search social and news for the claim and log each source and its reach
  3. Split the rumor into separate checkable claims
  4. Ask the fact owners to confirm each claim with a record
  5. Draft a fact sheet answering each claim with its source
  6. Is every statement in the sheet backed by a confirmed record?If not: hold back the statement and ask the owner again for proof. Back to step 3.
  7. Manager approves what is published and whereThe agent waits here for your OK.
  8. Publish through the approved channels
  9. Re-check spread and sentiment after 2 hours
  10. Is the rumor still growing?If not: re-run the search, update the claim list and the sheet, and send to the manager again. Back to step 2.
  11. Final summary and monitoring plan

How it decides

A claim is answered only when a named owner has confirmed the fact with a document or record. Spread is rated by reach and growth per hour.

  • Publish a fact only when an owner has confirmed it in writing
  • Hold back any unverified point rather than guess
  • Rate spread high when reach doubles within 3 hours
  • Say clearly which part of a claim is true if it is partly true

Make it yours

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

  • Monitoring sources and keywords
  • Fact owners per topic
  • Spread alert threshold
  • Re-check interval (default 2 hours)
  • Channels for publishing

What keeps you in control

It always asks you first

  • Manager approves every published statement
  • Manager approves contacting outlets

Hard limits

  • Never publish unverified facts
  • Do not engage with accounts spreading the claim without approval

It stops when

  • Done: spread has stopped growing for 24 hours
  • Stop: legal puts a hold on the facts, pause and inform the manager

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 happensA post claims a plant was closed for failed safety audits. The agent logs 14 posts reaching about 90,000 people. Operations confirms the plant paused for a scheduled upgrade, but the audit claim has no record, so the agent holds it. The sheet is drafted with the upgrade dates. Safety then supplies the clean 2024 audit report, and the sheet is updated. The manager approves publishing on the website and to two outlets.

More agents for crisis communications managers

Communication · PR and communications

Press Inquiry Coordination Agent

Accurate, approved press responses before the journalist's deadline.

7 steps1 check5 jobs
Quality control · PR and communications

Crisis Information Verification Agent

A verified-facts brief that leadership can trust minute by minute.

7 steps1 check6 jobs
Quality control · PR and communications

Media Correction Evidence Agent

Correction requests that are justified and precise.

8 steps2 checks4 jobs
Quality control · Automation

Crisis Holding Statement Readiness Agent

Make every crisis scenario have a current, approved holding statement with reachable approvers.

11 steps2 checks1 job