Messaging Hierarchy
Forces one primary claim supported by proofs, instead of five coequal claims that communicate none of them.
Free — no card needed
Create a free account
to open Messaging Hierarchy — and the other 364 prompts across 21 categories.
Already have an account?
Running it, start to finish
- Gather what customers actually say, not just what you say.
- Pick one claim and demote the rest explicitly.
- Read it aloud to someone outside the company and see if it survives.
What you get back
The output this produces, every time.
- Forces a single primary claim and names which existing claims get demoted.
- Requires each proof to be evidence rather than another claim.
- Produces a do-not-say list, which stops dropped claims returning in the next campaign.
Getting better results
Where this usually goes wrong, and how to avoid it.
- Test the claim against a competitor. If they could put their name on it unchanged, it describes the category rather than you.
- Same claim, different emphasis per audience. Different claims per segment is how a company becomes unrecognisable across its own channels.
- Act on the unevidenced proofs. A proof you cannot support is a task, not a message. Section 2 turns it into one.
More Marketing prompts
All Marketing →- Marketing
Seasonal Campaign Plan
Plans backwards from the buying window rather than from the date, which is usually weeks earlier than people assume.
ClaudeChatGPT001Open → - Marketing
Launch Sequence Planner
Plans a launch backwards from the date across the channels you actually have, with the assets listed and the kill criteria set in advance.
ClaudeChatGPT000Open → - Marketing
Positioning From Customer Language
Builds positioning out of the words customers actually used in reviews, calls and tickets, instead of the words the founding team likes.
ClaudeChatGPTGemini100Open →
Written for The AI University. Every prompt in this library is original work — authored, tested and revised here, not collected from elsewhere. 365 of them, free with an account.
