Prompt
You are helping a copywriter produce test variants of {{asset_type}} for {{brand}}.

The offer or message, and the facts behind it (use only these — invent no new benefit or number): {{offer_and_facts}}

Hard constraint: each variant must be {{limit}} or shorter. Count and show the character length of each.

Produce 15 variants, three each across these five angles, and label every one with its angle:
- Direct benefit
- Curiosity / open loop
- Objection or risk reversal
- Social proof (only if the facts include a real proof point)
- Specific / number-led

Rules:
- Every variant must be defensible from the facts I gave you. If an angle has no supporting fact (e.g. no real social proof), write "no supporting fact provided" instead of fabricating one.
- No clickbait that the copy can't pay off. No ALL CAPS, no more than one emoji, no "clinically proven" or superlatives unless the fact supports them.
- Vary sentence shape, not just word swaps.

Fill in your details and the prompt updates live — then copy.

What you get back (excerpt)

Direct benefit — "Covered in 190 countries, sorted today" (38) Direct benefit — "Travel insurance without the fine-print maze" (44) Curiosity — "The claim we paid in 48 hours" (30) Objection — "Cancel anytime. We mean it." (28) Objection — "Not sure you need it? Read this first" (38) Social proof — no supporting fact provided (no testimonial or user count given) Number-led — "20% off annual plans ends Friday" (32) Number-led — "48-hour claims, 190 countries" (29)

The full workflow

  1. Give the model the real offer and the facts behind it, plus the exact character limit
  2. Generate the batch, then cut anything that overpromises or that your product can't pay off
  3. Verify the character count in your actual email or ad platform, not just the model's count
  4. Test the two or three strongest against a human-written control before scaling

Watch out for

A subject line or headline is still an ad claim. If the copy behind it can't deliver what the line promises, it's deceptive under FTC truth-in-advertising rules — don't ship a variant you can't substantiate just because it tested well.

AI defaults to fabricating social proof ('join 10,000 happy customers'). Only use a proof point if it's real and current, and make the model flag angles it has no fact for rather than inventing one.

Where this comes from

Every use case on this site is grounded in real reports from working copywriters — not invented by us.

More AI use cases for copywriters

← All 6 use cases: How Copywriters Use AI