Check Ad Copy for Platform Policy Risks Before You Submit
Get a line-by-line review of your ad copy that flags personal-attribute language, unverifiable claims and before-after implications, with compliant rewrites.
You getTable, full clean version of the ad and three points to confirm against the platform's current ad…
Prompt
You are an ad compliance reviewer who checks paid social and search ads before submission.
I will paste my ad copy right after this message, plus the platform and product category. If either is missing, ask me for it in one short message and wait.
Review the copy line by line for three risk types: personal-attribute language (copy implying you know the viewer's health, finances, age, ethnicity, religion or similar, such as "Struggling with debt?"), unverifiable or absolute claims (guarantees, "best", "cure", specific results without proof), and before-after implications (time-bound transformations of a body, income or life).
Rules:
- Quote the exact phrase that triggers each flag.
- Rate each flag Low, Medium or High with a one-sentence reason.
- Each rewrite keeps the original selling point and stays close to the original length.
- Do not invent statistics, studies or testimonials; if a claim needs proof, say what proof I would need.
- Mark lines with no issues as Clear and leave them unchanged.
Output format:
1. Table: Line # | Original | Flagged phrase | Risk type | Severity | Compliant rewrite
2. Full clean version of the ad, ready to paste.
3. Three points to confirm against the platform's current ad policy.
End with one line noting that policies change often, this is not legal advice, and regulated categories like health, finance or housing may need a lawyer's review.Example output
Tips and common edits
Why this works
- Naming three specific risk types gives the model a checklist instead of a vague 'is this compliant?' judgment.
- Quoting the exact trigger phrase and rating severity shows you what to fix first and why.
- Banning invented proof stops the rewrite from swapping one unverifiable claim for another.
Use before submitting ads to Meta, Google or TikTok. Paste your headline, primary text and description into ChatGPT, Claude or Gemini, and name the platform and product category.
Common edits
- Add a fourth risk type, such as trademark use or sensational language, for your industry.
- Ask for three rewrite options per flagged line so you can A/B test compliant versions.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Write Facebook and Instagram Ad Copy in Pain, Outcome and Curiosity Angles
Get three ready-to-test Meta ad variations, each with primary text hooked in the first 125 characters, a headline, a description and a CTA button.
Audit an Underperforming Ad and Rewrite It With a Reason for Every Change
Get a pass/fail audit of your pasted ad on four copy checks, two rewrites that test different angles, and a change log tying every edit to a failed check.
Write a YouTube Pre-Roll Ad Script That Lands Before the Skip Button
You get a timed YouTube pre-roll script that delivers your brand and core promise in the first five seconds, plus a 6-second bumper cut and two alternative hooks.
Turn Customer Pain Points into 20 Ad Hooks Ranked by Specificity
You get 20 short ad hooks split into question, statement and scenario types, each tied to a real pain point and ranked by how concrete it is.
Write 10 Ad Variations That Each Test One Variable Against a Control
You get a control ad plus 10 single-change variants (hook, offer framing or CTA), each with a labeled hypothesis and primary metric so A/B test results are easy to read.
Build a Brand Voice Guide From Your Own Sample Copy With Do and Don't Rewrites
You get a brand voice guide drawn from your pasted copy, with trait tables, channel tone rules, before/after rewrites, a banned-word list and a quick checklist.