Ads & Campaigns

Verified against ChatGPT · 2026-08-10

Write a paid-media campaign brief tight enough that a media buyer and a designer build the same campaign

Produces a single-source campaign brief with the objective, audience, budget split, and creative direction locked to specific numbers and constraints, so the media buyer and the designer don't quietly build two different campaigns from the same kickoff meeting.

ChatGPT (GPT-5.1)5 fillable variables

The prompt

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

Write a paid-media campaign brief for the launch described below. The test for whether this brief succeeded: a media buyer and a designer who have never spoken to each other should be able to read only this document and build the same campaign, with no assumptions filled in differently by each of them.

CAMPAIGN OBJECTIVE AND SUCCESS METRIC
Generate 150 qualified demo signups for the new mid-market tier by end of Q3.

TARGET AUDIENCE
Ops managers at 50-200 employee logistics companies; explicitly not enterprise (>1000 employees) or solo founders.

BUDGET AND FLIGHT DATES
$22,000 total, flighting Sept 1 to Sept 30.

CHANNELS APPROVED FOR THIS CAMPAIGN
LinkedIn ads and Google Search only — no Meta this cycle per leadership decision.

HARD CONSTRAINTS
Must not use the word "guaranteed" anywhere in ad copy; logo must appear at full size, not cropped.

BRIEF REQUIREMENTS
State the objective as a single measurable outcome with a target number and a deadline, not a vague direction like "drive awareness" — if objective_and_success_metric doesn't already include a number, flag that as a gap the brief cannot responsibly fill in for the team and name it explicitly rather than inventing a plausible-sounding target. Split the budget across the approved channels with a stated rationale for the split, not an even default division — an even split across channels is itself a decision that should be justified or explicitly avoided, since channels rarely deserve equal spend by default. Write the creative direction section specifically enough that two different designers would produce visibly similar output: name the emotional register, what the visual must NOT look like (competitor brief-fatigue is real — call out a specific competitor's visual style to avoid if one is relevant), and the one non-negotiable brand or legal element that must appear in every asset. Every hard constraint given must appear as an explicit line in the brief itself, not just be honored implicitly in your reasoning — a constraint a reader can't see in the document isn't actually a constraint on the team building from it.

OUTPUT FORMAT
1. Objective (one sentence, one number, one deadline) — or an explicit flag if the input doesn't support one.
2. Audience (who, and just as important, who this is NOT for).
3. Budget table by channel with one-line rationale per row.
4. Flight timeline.
5. Creative direction (register, what to avoid, non-negotiable element).
6. Hard constraints, restated as a checklist.
7. One open question the brief cannot answer on its own and needs a decision-maker to close before work starts.

Customize

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

Why this works

A campaign brief fails silently, not loudly — the media buyer and the designer each fill any ambiguity in the document with their own private assumption, and the gap only surfaces at review, after money has already been spent and creative already built, which is the single most expensive place to discover a brief was underspecified. Forcing an explicit number and deadline into the objective line, and instructing the model to flag rather than invent one when the input lacks it, prevents GPT-5.1's default behavior of smoothing a vague goal like "drive awareness" into a plausible-sounding but fabricated target, which would let the brief look complete while actually deferring the hardest decision to whoever reads it last. Requiring a budget-split rationale rather than accepting an even division across channels matters because an even split is a real, common failure mode of both AI-generated and human-written briefs — it looks fair and defensible on paper while almost never matching the actual cost-efficiency differences between channels like LinkedIn and Google Search for the same audience. The instruction that every hard constraint must appear as a visible line in the document, not just be respected implicitly in the model's reasoning, addresses a specific and easy-to-miss failure: a constraint honored inside the model's generation but never surfaced as text is invisible to the human team executing the brief days later, who has no way to know it was ever considered unless it's written down as an explicit line they can check work against.

What you get back

Objective: Generate 150 qualified demo signups for the mid-market tier by Sept 30. Budget: LinkedIn $15,000 (70% — audience is only reliably addressable there via job-title targeting), Google Search $7,000 (30% — captures existing intent from competitor and category terms, lower expected volume this audience size). Open question: leadership hasn't confirmed whether "qualified" means BANT-qualified or just form-completed — this determines whether the campaign is actually hitting 150 or a smaller real number, and needs a decision before spend starts.

Verified against

ChatGPT GPT-5.1 · 2026-08-10

Changelog

  • 2026-08-10 — 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