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

Crisis Information Verification Agent

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

Crisis Information Verification Agent: what goes in, what the agent does and what you get

What it does

During a crisis, unverified updates mix with confirmed facts, and statements can go out wrong. When an incident is declared and with each new update, this agent separates attributed claims from confirmed facts. When updates conflict, it starts with the conflict that matters most and asks the named authoritative source, such as the operations lead, to confirm. Contradictions stay visible in the brief until they are resolved. It drafts communications using only approved facts. The incident communications lead approves every public statement and any conclusion about the incident. Edge case: two reports give 1,200 and 3,400 affected customers, so both stay shown until operations confirms.

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, continueApprovedNo 1 STARTS WHEN Incident update 2 USES A TOOL Separate claims from confirmed facts 3 CHECKS THE RESULT Do updates conflict? If not: (no conflict) continue. Back to step 2. 4 USES A TOOL Seek confirmation from the named source 5 DOES Update the brief with contradictions visible 6 YOU APPROVE Incident communications lead approves statements 7 RESULT Verified-facts brief and draft
Read the steps as a list
  1. Incident update
  2. Separate claims from confirmed facts
  3. Do updates conflict?If not: (no conflict) continue. Back to step 2.
  4. Seek confirmation from the named source
  5. Update the brief with contradictions visible
  6. Incident communications lead approves statementsThe agent waits here for your OK.
  7. Verified-facts brief and draft

How it decides

It verifies the most consequential conflict first and promotes only approved facts.

  • Drafts use only approved facts.
  • Contradictions stay visible until a named source confirms.
  • Resolve the most consequential conflict first.

Make it yours

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

  • Named authoritative source per fact type
  • Update interval for the brief (default every 30 minutes)
  • Statement templates for each channel
  • Who approves public statements

What keeps you in control

It always asks you first

  • Public statements
  • Incident conclusions
  • Sensitive disclosures

Hard limits

  • No public statements.

It stops when

  • Done: incident closed.

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 happensAt 08:40 on 22 February a service outage is declared. By 09:15, two reports say 1,200 and 3,400 affected customers. The conflict check fails, so the agent asks the operations lead and keeps both numbers visible. At 09:40 the lead confirms 3,400. The agent promotes that fact and drafts a customer statement. The incident communications lead approves the statement at 09:55.

More agents for crisis communications managers