Back to gallery

Marketing

Facebook Ad Copy Framework

Create distinct paid-social ad angles without repeating the same claim.

Models
ChatGPT, Claude
Level
Beginner
Version
v0.9
01

What this prompt does

Create distinct paid-social ad angles without repeating the same claim.

02

Best for

An angle matrix, primary text, headline, CTA, visual direction, and claim-risk note for each concept.

03

Prompt variables

[PRODUCT][AUDIENCE][OFFER][PROOF]
System Prompt
You are a performance copywriter who separates evidence, audience tension, offer, and creative angle.
User Prompt
OBJECTIVE:
Develop five Facebook ad concepts for [PRODUCT] aimed at [AUDIENCE]. The offer is [OFFER]. Use only this proof: [PROOF].

INPUTS:
PRODUCT: [PRODUCT]
AUDIENCE: [AUDIENCE]
OFFER: [OFFER]
PROOF: [PROOF]

OUTPUT CONTRACT:
An angle matrix, primary text, headline, CTA, visual direction, and claim-risk note for each concept.

How to use

Replace every variable with specific, non-sensitive information. Remove irrelevant sections and add one representative example when tone or classification matters.

Why it works

The blueprint separates authority, task context, evidence limits, and the output contract so requirements can be checked independently.

Model compatibility

ChatGPTuntestedEditorial compatibility hypothesis; cross-model test record pending.

ClaudeuntestedEditorial compatibility hypothesis; cross-model test record pending.

05

Example input

PRODUCT: [PRODUCT]
AUDIENCE: [AUDIENCE]
OFFER: [OFFER]
PROOF: [PROOF]

06

Example output

A structured deliverable following the listed output contract, with assumptions and missing evidence clearly marked.

How to customize

Replace every variable with specific, non-sensitive information. Remove irrelevant sections and add one representative example when tone or classification matters.

Common mistakes

Do not paste secrets or personal data. Avoid contradictory constraints, unsupported facts, and using generated output without review.

Test notes

Editorial blueprint awaiting recorded cross-model evaluation. It is visible for review but is not labeled as tested.

Why is this blueprint not marked as tested?

It has passed editorial structure review but does not yet have a published cross-model test record.