Ads & Campaigns

Verified against ChatGPT · 2026-08-11

Build an AIDA ad campaign that stays coherent across three channels instead of three disconnected pitches

Writes a full AIDA-structured ad campaign (Attention, Interest, Desire, Action) with one variant per channel, keeping the same core argument intact across channels while adapting format and length to each platform's actual constraints.

ChatGPT (GPT-5.1)5 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

Build an AIDA-structured ad campaign for A 14-day free trial of a habit-tracking app with no credit card required., across the channels listed below — the constraint is that all channel variants must argue the same underlying case in the same order, adapted only for format and length, not turn into three unrelated pitches that happen to share a product name.

OFFER
A 14-day free trial of a habit-tracking app with no credit card required.

CHANNELS IN THIS CAMPAIGN
Facebook feed ad, Google Search ad, SMS reminder to warm leads.

TARGET AUDIENCE
People who downloaded a productivity ebook lead magnet in the last 30 days but haven't converted.

SINGLE CORE ARGUMENT THE WHOLE CAMPAIGN MAKES
You already know what you want to change — this just removes the friction of tracking it.

CAMPAIGN TIMEFRAME OR URGENCY DRIVER
Free trial offer ends when the lead magnet email sequence ends, in 5 days.

For each channel, write the four AIDA beats (Attention, Interest, Desire, Action) as actual copy, not as labeled abstractions — each beat should be recognizable copy a person would actually see, sized to the channel (a Facebook feed ad has room for a paragraph across Attention through Desire; a Google Search ad has to compress all four beats into two headlines and one description; an SMS or push notification variant may only have room for Attention and Action, in which case say so rather than forcing Interest and Desire into a text that has no room for them). Every channel's Attention beat must map to the same core argument, even though the wording differs — if you find yourself writing a genuinely different argument for one channel because the format demands it, flag that explicitly rather than silently drifting off-message. Do not fabricate the urgency driver if none was given — if Free trial offer ends when the lead magnet email sequence ends, in 5 days. is empty, build Action beats that don't rely on manufactured scarcity or countdown language.

OUTPUT: one section per channel (Channel name, then Attention/Interest/Desire/Action as actual copy, noting which beats a length-constrained channel had to compress or drop), followed by a one-paragraph cross-channel consistency check confirming the core argument holds across all variants or flagging where it drifted and why.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

AIDA is a sequencing framework, not a length or format spec, so a prompt that just asks for "an AIDA ad for each channel" tends to produce three copy pieces that each individually follow the four beats internally but drift apart from each other in underlying argument, because the model treats each channel as a fresh writing task rather than a constrained restatement of one fixed thesis — explicitly stating the single core argument up front and requiring a consistency check at the end forces the model to treat channel variants as the same argument under different compression, which is what actually keeps a multi-channel campaign feeling coherent to someone who sees the Search ad, then gets retargeted with the Facebook ad, then receives the SMS. Requiring the model to acknowledge when a length-constrained channel (SMS, push notification) has to drop Interest or Desire entirely rather than forcing all four beats into a format with no room for them addresses a real structural mismatch: AIDA was designed for long-form print copy, and applying it uncritically to a 160-character SMS produces cramped, illegible copy where a model will otherwise try to hit all four beats regardless of whether the format supports it. The instruction against manufacturing urgency when none was given directly guards against a known default behavior — models asked for an Action/CTA beat under time pressure reach for countdown-timer and "ends soon" language by default, which becomes a false-urgency compliance issue in ad platforms that increasingly flag manufactured scarcity, and is also a trust cost the first time a repeat visitor notices the "ending soon" offer never actually ends.

What you get back

SMS variant (Attention/Action only, Interest/Desire dropped — no room in 160 characters): Attention+Action combined: "You've got 5 days left on your free trial of [App] — no card needed. Open the app and log today's habit: [link]" Consistency check: retains the core argument (removing tracking friction) implicitly through the CTA itself rather than restating it, which is the only viable compression given the channel's length limit.

Verified against

ChatGPT GPT-5.1 · 2026-08-11

Changelog

  • 2026-08-11 — Initial publish, verified against ChatGPT GPT-5.1.

Need this built into your business?

If a prompt isn't enough — Google Ads management, built and maintained for you — that's Scult's day job.

EXPLORE GOOGLE ADS MANAGEMENT
All Ads & Campaigns prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY