AI agent for communication managers
Executive Message Alignment Check Agent
Bring every leader's public wording in line with the approved key messages.
What it does
Before a big campaign, you need every leader to describe the strategy the same way. This agent gathers recent speeches, emails, town hall transcripts and interview quotes from each leader, then compares them with the approved key messages. It marks each statement as aligned, drifting or contradicting, and shows the exact phrase. For problems it proposes wording that fits the message house and keeps the leader's own style. When leaders revise their drafts, it rechecks the new version against the same messages. You decide what goes back to each leader. Edge case: one leader calls a reorg a restructuring and another calls it a transformation, and the agent flags the wording mismatch with the approved term.
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.
Read the steps as a list
- Campaign brief and message house are approved
- Gather recent statements from each leader
- Break each statement into claims
- Compare every claim with the approved messages
- Does each claim match the approved messages?If not: Mark each claim as drifting or contradicting with the exact phrase. Back to step 4.
- Propose aligned wording in the leader's own style
- Communications lead approves what goes back to each leaderThe agent waits here for your OK.
- Send approved suggestions and collect revised drafts
- Recheck revised drafts against the message house
- Are all revised drafts aligned?If not: Return the remaining differences with new suggestions. Back to step 5.
- Alignment report by leader
How it decides
It compares meaning first, then wording. A contradiction is a conflict in fact or direction. Drift is different wording for the same fact.
- Contradictions in fact are flagged high, wording drift medium
- Approved terms in the glossary replace local variants
- Never suggest wording that changes a fact
- A leader is aligned only when no claim is flagged high
Make it yours
Every agent is a starting point. You choose these settings for your own situation.
- Severity levels for contradictions and drift
- Leaders included
- Approved glossary terms
- Sources to scan
- Recheck deadline (default 3 days)
What keeps you in control
It always asks you first
- Anything sent to a leader
- Changes to the approved message house
Hard limits
- Never changes the approved messages
- Never shares one leader's draft with another
- Keeps a record of what it suggested
It stops when
- Done: all leaders aligned
- Stop: leaders disagree with the message house; the lead decides
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.
- 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